© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16087
    Prev
    Next
    INDEX
    Explanations

    code, HTML, and punctuation

    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
    ç»ĵ交
    -0.07
    表çİ°åĩºæĿ¥çļĦ
    -0.06
    åIJİä¼ļ
    -0.06
    VERSION
    -0.06
    ãĥIJãĥ³
    -0.06
    该款
    -0.06
    _traits
    -0.06
    _MON
    -0.06
     Examination
    -0.06
    appoint
    -0.06
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.08
    åĬłæĭ¿å¤§
    0.08
    èĵ¬
    0.08
    iscal
    0.08
    áo
    0.08
    æĺĻ
    0.07
    æĿ¥åIJ§
    0.07
    euse
    0.07
    纨
    0.07
    AMY
    0.07
    Activations Density 0.058%

    No Known Activations