© 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. 58283
    Prev
    Next
    INDEX
    Explanations

    cardiac death

    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
    Ắ
    -0.07
    ffre
    -0.07
    ound
    -0.07
    amak
    -0.07
    éĵ¶å±±
    -0.07
    å·´æĸ¯
    -0.07
    念
    -0.06
    SE
    -0.06
    дÑĢ
    -0.06
    rone
    -0.06
    POSITIVE LOGITS
    lesh
    0.09
    å¥ķ
    0.08
    wat
    0.07
    зем
    0.07
    ä¸ĢæĹı
    0.07
    igent
    0.07
    getConfig
    0.07
     lives
    0.07
    chand
    0.07
    خش
    0.07
    Activations Density 2.082%

    No Known Activations