© 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. 4033
    Prev
    Next
    INDEX
    Explanations

    2019; or 2020;

    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
    å½ĵåľ°
    -0.07
    onat
    -0.07
    æĿ¥äºĨ
    -0.07
     wide
    -0.06
    å½ĵåľ°æĶ¿åºľ
    -0.06
    wide
    -0.06
    ×IJ×Ļ×Ŀ
    -0.06
    缴è§Ĩ
    -0.06
    åľ¨ä¿Ŀè¯ģ
    -0.06
    wp
    -0.06
    POSITIVE LOGITS
    åīįç¨ĭ
    0.07
    ITT
    0.07
    lore
    0.07
     سط
    0.07
    éĻ
    0.07
    ape
    0.07
    ugend
    0.06
    entina
    0.06
    imaan
    0.06
    utz
    0.06
    Activations Density 0.002%

    No Known Activations