© 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. 58469
    Prev
    Next
    INDEX
    Explanations

    Counting or categorizing items

    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
     pixels
    -0.07
     Rout
    -0.07
     goodwill
    -0.07
     ROW
    -0.06
    芰
    -0.06
    焰
    -0.06
    WEB
    -0.06
     ard
    -0.06
     glVertex
    -0.06
    这才是
    -0.06
    POSITIVE LOGITS
    铊
    0.08
    EGA
    0.07
    "><?=$
    0.07
     peru
    0.07
    <?=$
    0.07
    =no
    0.07
    ><?=$
    0.07
    Lou
    0.07
    ,L
    0.07
    >{{$
    0.06
    Activations Density 0.013%

    No Known Activations