© 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. 13454
    Prev
    Next
    INDEX
    Explanations

    json, midi, code lists

    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
     ourselves
    -0.07
    /
    -0.07
    omen
    -0.07
    raven
    -0.06
    ül
    -0.06
    pro
    -0.06
    å²Ĥ
    -0.06
    è±
    -0.06
    for
    -0.06
    ãģ¾ãģĹãģ¦
    -0.06
    POSITIVE LOGITS
    请åijĬçŁ¥
    0.09
    htub
    0.08
    penas
    0.07
    åĬłæĭ¿å¤§
    0.07
    æľīåĬł
    0.07
    请æĶ¾å¿ĥ
    0.07
    typings
    0.07
    请åĬł
    0.07
    æĸ°åĬłåĿ¡
    0.07
    RYPT
    0.07
    Activations Density 0.033%

    No Known Activations