© 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. 39891
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    wk
    -0.08
    uchi
    -0.08
    åį·åħ¥
    -0.07
    rb
    -0.07
    uld
    -0.07
     involved
    -0.07
    èµ·äºĨ
    -0.07
    otron
    -0.07
    _inactive
    -0.07
    纨
    -0.07
    POSITIVE LOGITS
    åľ¨ç»ıè¿ĩ
    0.08
     {?}
    0.07
    åĨħ容为
    0.07
    æĹ¶è¡¨ç¤º
    0.07
    ä¸Ģ串
    0.07
     Cay
    0.06
    istring
    0.06
    _unlock
    0.06
    åĨħ容åĮħæĭ¬
    0.06
    åĨħ容æĺ¯
    0.06
    Activations Density 0.005%

    No Known Activations