© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9665
    Prev
    Next
    INDEX
    Explanations

    male, female, majority, distribution, White

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amp
    -0.07
    eff
    -0.07
    Selective
    -0.07
    äºİå¿ĥ
    -0.06
     rej
    -0.06
    è£ģ
    -0.06
    å¤©åľ°
    -0.06
    åIJĮåı·
    -0.06
    eho
    -0.06
    çŃĸ
    -0.06
    POSITIVE LOGITS
    åĪĨå¸ĥå¦Ĥä¸ĭ
    0.13
     majority
    0.13
    åĪĨå¸ĥ
    0.13
     predomin
    0.13
     predominantly
    0.12
     Distribution
    0.12
     distribution
    0.12
    大éĥ¨åĪĨéĥ½æĺ¯
    0.11
    大å¤ļæĺ¯
    0.11
    å±ħå¤ļ
    0.11
    Activations Density 0.668%

    No Known Activations