© 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. 9349
    Prev
    Next
    INDEX
    Explanations

    ID | Year | Factor1

    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
    egral
    -0.07
    pig
    -0.07
    è¿ijæĿ¥
    -0.07
    елÑı
    -0.06
    isst
    -0.06
     allerlei
    -0.06
    (crate
    -0.06
    binations
    -0.06
    odesk
    -0.06
    anken
    -0.06
    POSITIVE LOGITS
    astas
    0.08
    ä¸ĢæľŁå·¥ç¨ĭ
    0.07
    é¦ĸåħĪ
    0.07
    ëĭ¤ë©´
    0.07
    utta
    0.07
    å¦Ĥæŀľè¯´
    0.07
    è¿ĶåĽŀ顶éĥ¨
    0.07
    mq
    0.07
     pertama
    0.07
    è´¨çļĦ
    0.07
    Activations Density 0.031%

    No Known Activations