© 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. 3074
    Prev
    Next
    INDEX
    Explanations

    prime factors

    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
    ush
    -0.08
    initial
    -0.07
    ưỡng
    -0.07
    交
    -0.07
     initial
    -0.07
    ot
    -0.06
    ä¸ĢæĿ¡æĿ¡
    -0.06
    交çļĦ
    -0.06
    itches
    -0.06
    è¾¾æĭī
    -0.06
    POSITIVE LOGITS
    _WAKE
    0.08
    apl
    0.08
    cid
    0.08
    éĹ®ä¸Ģä¸ĭ
    0.07
     feu
    0.07
    yun
    0.07
    å¤ĸ人
    0.07
    føl
    0.07
    ỵ
    0.07
    дом
    0.07
    Activations Density 0.002%

    No Known Activations