© 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. 434
    Prev
    Next
    INDEX
    Explanations

    numerical increases

    np_max-act · gemini-2.0-flash
    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
    ableObject
    -0.07
    珩
    -0.07
    ῶ
    -0.07
    诏
    -0.07
     infield
    -0.06
     yok
    -0.06
    席
    -0.06
    Fashion
    -0.06
    .watch
    -0.06
    alance
    -0.06
    POSITIVE LOGITS
    回报
    0.09
    솥
    0.08
    存活
    0.08
     personalized
    0.08
     סרט
    0.08
    ambiguous
    0.07
    ovie
    0.07
     podem
    0.07
     Carl
    0.07
     precise
    0.07
    Activations Density 0.105%

    No Known Activations