© 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. 9202
    Prev
    Next
    INDEX
    Explanations

    inhibits or decreases

    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
    uzzi
    -0.08
    èı²èı²
    -0.08
    PrototypeOf
    -0.07
    OMIC
    -0.07
    hä
    -0.07
    åľ¨å®ĮæĪIJ
    -0.07
    èŁĨ
    -0.07
    æ§ĥ
    -0.07
    prise
    -0.07
    oner
    -0.07
    POSITIVE LOGITS
    çļĦç¨ĭ度
    0.07
    丽ä¸Ŀ
    0.07
    èĥİ
    0.07
    undef
    0.07
    ä»ħ代表
    0.06
    åĽŀ
    0.06
    ivs
    0.06
    Ir
    0.06
    opr
    0.06
    ajar
    0.06
    Activations Density 0.336%

    No Known Activations