© 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. 10412
    Prev
    Next
    INDEX
    Explanations

    #include < library

    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
    ÑĤони
    -0.07
    ikuti
    -0.07
    aeda
    -0.07
    è®°åĪĨ
    -0.07
    Serialize
    -0.07
    itano
    -0.07
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.07
    ircles
    -0.07
     Roose
    -0.07
    缸çľĭ
    -0.06
    POSITIVE LOGITS
    OPS
    0.07
    FM
    0.07
    perator
    0.07
    Ñħов
    0.07
    éĢ¸
    0.06
    мÑĭÑĪ
    0.06
     поÑģл
    0.06
    ertools
    0.06
    chos
    0.06
    æ½ľ
    0.06
    Activations Density 0.032%

    No Known Activations