© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2657
    Prev
    Next
    INDEX
    Explanations

    http:// links

    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
    _EXTENDED
    -0.07
    inston
    -0.07
    oges
    -0.07
    åŃ£åĨĽ
    -0.07
     sourceMapping
    -0.07
    ucho
    -0.06
    &gt
    -0.06
     ([[
    -0.06
    æ°¸åħ´
    -0.06
    ils
    -0.06
    POSITIVE LOGITS
    gger
    0.07
     nữa
    0.07
    kening
    0.07
    تÙħÙĬ
    0.06
     Hurricanes
    0.06
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.06
    itzer
    0.06
    ordert
    0.06
    erei
    0.06
    lam
    0.06
    Activations Density 0.149%

    No Known Activations