© 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. 19786
    Prev
    Next
    INDEX
    Explanations

    git diff headers

    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
    าม
    -0.08
    оÑĢи
    -0.08
    æĸ°è¯¾ç¨ĭ
    -0.07
     Zam
    -0.06
    fert
    -0.06
    æĪij们认为
    -0.06
    leit
    -0.06
    emis
    -0.06
    Ĩ
    -0.06
    getti
    -0.06
    POSITIVE LOGITS
    hower
    0.07
    è¿Ľè¡Į管çIJĨ
    0.07
     scha
    0.07
    骸
    0.07
    accio
    0.07
    loat
    0.07
    kaus
    0.06
    è¿ŀäºij
    0.06
    ieber
    0.06
    theless
    0.06
    Activations Density 0.001%

    No Known Activations