© 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. 21976
    Prev
    Next
    INDEX
    Explanations

    #ifdef, Timer, Pool

    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
    åģıåģı
    -0.07
    _-_
    -0.07
    obi
    -0.06
    iquid
    -0.06
    bish
    -0.06
    bow
    -0.06
    å¤ļç±³
    -0.06
    åĨľæĿij人å±ħçݯå¢ĥ
    -0.06
    ies
    -0.06
    bh
    -0.06
    POSITIVE LOGITS
    arz
    0.08
    å©Ģ
    0.08
    åĨħ线
    0.07
    sider
    0.07
    pls
    0.07
    天èµIJ
    0.07
    å¿ĹæĦ¿èĢħçļĦ
    0.07
    fone
    0.07
    gress
    0.07
    gres
    0.07
    Activations Density 0.137%

    No Known Activations