© 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. 15-RESID-POST-AA
    11. 30147
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichTextBox
    -0.08
    כול
    -0.07
    (info
    -0.07
    뻑
    -0.07
     R
    -0.07
    ucher
    -0.07
    -Class
    -0.07
    SEQUENTIAL
    -0.07
     criança
    -0.07
     médica
    -0.07
    POSITIVE LOGITS
     outcry
    0.07
    Gram
    0.07
    (layer
    0.07
    ade
    0.07
    抗体
    0.07
     undergo
    0.06
    (write
    0.06
    刽
    0.06
    向社会
    0.06
     stomach
    0.06
    Activations Density 0.005%

    No Known Activations