© 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. 17521
    Prev
    Next
    INDEX
    Explanations

    chem

    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
     mise
    -0.07
    .a
    -0.07
    COME
    -0.07
    的同学
    -0.07
     wires
    -0.07
     две
    -0.07
     المؤتمر
    -0.06
     Kong
    -0.06
    恐龙
    -0.06
     şimdi
    -0.06
    POSITIVE LOGITS
    事实
    0.07
    pheric
    0.07
     disturbed
    0.06
    uniform
    0.06
     unab
    0.06
    .getStatusCode
    0.06
     TOP
    0.06
    &,
    0.06
     lifestyle
    0.06
    основ
    0.06
    Activations Density 0.000%

    No Known Activations