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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 58741
    Prev
    Next
    INDEX
    Explanations

    ::

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ooke
    -0.07
    缔
    -0.07
     lesen
    -0.07
    摆放
    -0.07
    (optional
    -0.07
     soothing
    -0.07
    (header
    -0.06
    USAGE
    -0.06
     delicate
    -0.06
    كه
    -0.06
    POSITIVE LOGITS
     successor
    0.07
    였
    0.06
     ancestor
    0.06
    Ark
    0.06
    崃
    0.06
    warz
    0.06
     bó
    0.06
    ност
    0.06
    流产
    0.06
    整整
    0.06
    Activations Density 0.010%

    No Known Activations