© 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. 27621
    Prev
    Next
    INDEX
    Explanations

    works fine

    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
     Sho
    -0.08
    ugna
    -0.08
    autor
    -0.07
    imore
    -0.07
    istere
    -0.07
    ANY
    -0.07
    ×Ĵר
    -0.07
    åĪ°åºķæĺ¯ä»Ģä¹Ī
    -0.07
    oram
    -0.07
    .bz
    -0.07
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.09
     prelimin
    0.07
    åĪĿæŃ¥
    0.07
    èµ·
    0.07
    第ä¸Ģ个
    0.06
    第ä¸ĢæĿ¡
    0.06
     ðŁij
    0.06
     den
    0.06
    สà¹Į
    0.06
    女
    0.06
    Activations Density 0.028%

    No Known Activations