© 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. 27728
    Prev
    Next
    INDEX
    Explanations

    mathematical and code expressions

    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
    nock
    -0.08
    jaa
    -0.07
    ãģ¡ãĤĥ
    -0.07
    жÑĥ
    -0.07
    è·Įå®ķ
    -0.07
     #####
    -0.07
    åĨ³å®ļæĺ¯åIJ¦
    -0.06
    èĬ®
    -0.06
    äd
    -0.06
    èį£åħī
    -0.06
    POSITIVE LOGITS
    inster
    0.09
    amana
    0.07
    å®ĥå°±æĺ¯
    0.07
    èĤĨ
    0.07
     cali
    0.07
    rez
    0.07
    íķĺë©´
    0.07
    ussy
    0.06
    çļĦæľĭåıĭåı¯ä»¥
    0.06
    å°Ķæĸ¯
    0.06
    Activations Density 0.016%

    No Known Activations