© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 7990
    Prev
    Next
    INDEX
    Explanations

    Biological mechanisms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -general
    -0.07
     Adventure
    -0.07
    说不定
    -0.07
    ért
    -0.07
    🥦
    -0.07
    に関する
    -0.07
    дель
    -0.07
    陆军
    -0.06
     McDonald
    -0.06
     Platt
    -0.06
    POSITIVE LOGITS
    "،
    0.08
    _PHASE
    0.07
    odied
    0.07
    量
    0.07
     simil
    0.07
    трат
    0.07
     Turns
    0.07
    iscrimination
    0.07
    .Est
    0.07
     строк
    0.07
    Activations Density 0.077%

    No Known Activations