© 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. 10189
    Prev
    Next
    INDEX
    Explanations

    vasoconstriction

    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
    _spaces
    -0.08
    ạm
    -0.08
    shal
    -0.07
    ضة
    -0.07
    æĺ±
    -0.07
    иж
    -0.07
    .EXTRA
    -0.07
    éĢŁ
    -0.07
    αÏģ
    -0.07
    abi
    -0.07
    POSITIVE LOGITS
    åIJİéĿ¢çļĦ
    0.06
    iant
    0.06
    IfNeeded
    0.06
    iken
    0.06
    æĬ¥åijĬ书
    0.05
    ฯ
    0.05
    åıĪä¸į
    0.05
    quinas
    0.05
    çļĦä¸Ģ项
    0.05
     dia
    0.05
    Activations Density 0.003%

    No Known Activations