© 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. 15379
    Prev
    Next
    INDEX
    Explanations

    derivative of w, y, l

    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
     certain
    -0.09
    æŁIJäºĽ
    -0.08
     Certain
    -0.07
     surprisingly
    -0.06
     poorly
    -0.06
     ciertos
    -0.06
     Vol
    -0.06
    oto
    -0.06
     certaine
    -0.06
    åĬłå¿«
    -0.06
    POSITIVE LOGITS
    éĢIJ项
    0.08
    andi
    0.08
    åĬ²åĦ¿
    0.08
    enin
    0.07
    è¯ģæĺİ书
    0.07
    unpack
    0.07
    çİ¥
    0.07
    çŃīä»·
    0.07
    æ¯ıåħ¬æĸ¤
    0.07
    Former
    0.07
    Activations Density 0.087%

    No Known Activations