© 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. 31585
    Prev
    Next
    INDEX
    Explanations

    coding, Enum, ç¼ĸç¨ĭ

    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¿©ç¿©
    -0.07
    ä»Ĺ
    -0.07
    ptime
    -0.07
    μβ
    -0.07
    以赴
    -0.07
    ylim
    -0.07
    holt
    -0.06
    ắt
    -0.06
     rang
    -0.06
    åı½åı½
    -0.06
    POSITIVE LOGITS
    ÙĪØ´
    0.08
    lete
    0.07
    omen
    0.07
    £
    0.07
    urez
    0.07
    orando
    0.07
    forth
    0.07
    iera
    0.07
     Swan
    0.06
    otions
    0.06
    Activations Density 0.006%

    No Known Activations