© 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. 45586
    Prev
    Next
    INDEX
    Explanations

    chemotherapy, email, or codes

    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
    _primitive
    -0.07
    czo
    -0.07
    ption
    -0.07
    lah
    -0.07
    ä¸įç´Ĭ
    -0.07
    tre
    -0.06
    vet
    -0.06
    è¿ĺæķ¢
    -0.06
    rost
    -0.06
    ç´¯
    -0.06
    POSITIVE LOGITS
    ftware
    0.09
    ãĤĵ
    0.08
    æĸ°åĬłåĿ¡
    0.07
    ayne
    0.07
    rata
    0.07
    Ùħرة
    0.07
    ertype
    0.07
    ÑĢезÑĭ
    0.07
    adal
    0.07
    serde
    0.06
    Activations Density 0.001%

    No Known Activations