© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25054
    Prev
    Next
    INDEX
    Explanations

    surveys and polls

    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
    etter
    -0.07
    ciug
    -0.07
    nicz
    -0.07
    ogl
    -0.06
    Listing
    -0.06
    æľĿ代
    -0.06
    notation
    -0.06
    ä¼ģä¸ļæŁ¥è¯¢
    -0.06
    æ¬łç¨İåħ¬åijĬ
    -0.06
    ç»ıæµİæĸ°éĹ»
    -0.06
    POSITIVE LOGITS
     survey
    0.16
     surveys
    0.15
    éĹ®åį·
    0.15
    survey
    0.14
    éĹ®åį·è°ĥæŁ¥
    0.14
     questionnaire
    0.14
     surveyed
    0.14
     polled
    0.14
    è°ĥæŁ¥
    0.13
     Survey
    0.13
    Activations Density 0.432%

    No Known Activations