© 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. 11-RESID-POST-AA
    11. 4983
    Prev
    Next
    INDEX
    Explanations

    file paths and languages

    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
    ݒ
    -0.08
    支架
    -0.07
    .LAZY
    -0.07
    理念
    -0.06
    珇
    -0.06
    ประกอบ
    -0.06
    んですけど
    -0.06
    entrada
    -0.06
     essa
    -0.06
    镂
    -0.06
    POSITIVE LOGITS
     bc
    0.08
     ih
    0.07
     lettre
    0.07
    —who
    0.07
    ='';↵
    0.07
    “There
    0.06
     pi
    0.06
    (mi
    0.06
    —and
    0.06
    )::
    0.06
    Activations Density 0.004%

    No Known Activations