© 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. 9527
    Prev
    Next
    INDEX
    Explanations

    list items enclosed in parentheses or numbered

    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
    IOR
    -0.08
    loser
    -0.07
    è¡¥çŁŃ
    -0.07
    edr
    -0.07
    Statics
    -0.07
    alla
    -0.07
    amai
    -0.07
    à¸ģรà¹īà¸Ńà¸ĩ
    -0.07
    elay
    -0.07
    ecas
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.07
    ories
    0.06
    ä¸Ģ个
    0.06
    ¨
    0.06
    è¯ĿéŁ³
    0.06
    ateg
    0.06
    hum
    0.06
    ãģĵãģ¨ãĤĦ
    0.06
    icha
    0.06
    /><
    0.06
    Activations Density 0.019%

    No Known Activations