© 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. 41295
    Prev
    Next
    INDEX
    Explanations

    s

    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
     '';
    -0.09
    近两年
    -0.08
     "";
↵
↵
    -0.08
     ["
    -0.07
    indsay
    -0.07
    >";
    -0.07
    (decimal
    -0.07
    퍈
    -0.07
    (IEnumerable
    -0.07
    ,and
    -0.07
    POSITIVE LOGITS
    i
    0.12
    e
    0.12
    r
    0.12
    s
    0.11
    o
    0.11
    u
    0.10
    a
    0.10
    l
    0.10
    а
    0.09
    n
    0.09
    Activations Density 1.182%

    No Known Activations