© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 63
    Prev
    Next
    INDEX
    Explanations

    Liberalism

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of John Rawls’s work and key terms from his political‐liberal theory (e.g. Rawls, Political Liberalism, justice, fairness, normative principles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "//
    -0.07
    #ac
    -0.07
    -redux
    -0.07
     transforming
    -0.06
     Analy
    -0.06
    'e
    -0.06
    glyphicon
    -0.06
    >N
    -0.06
     प
    -0.06
    );?>↵
    -0.06
    POSITIVE LOGITS
    战术
    0.07
    endsWith
    0.07
    命令
    0.07
     şiddet
    0.07
    주민
    0.07
     letters
    0.07
    𥕢
    0.07
     דברים
    0.06
     Slayer
    0.06
     bets
    0.06
    Activations Density 0.010%

    No Known Activations