© 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. 46323
    Prev
    Next
    INDEX
    Explanations

    flux and related phenomena

    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
    ÅĽÄĩ
    -0.08
    lijke
    -0.08
    ãĤ¥
    -0.07
    liness
    -0.07
    -fashioned
    -0.07
    venz
    -0.07
    æĦıçļĦ
    -0.07
    ól
    -0.06
    bies
    -0.06
    hood
    -0.06
    POSITIVE LOGITS
    åĽĽå°Ħ
    0.12
    es
    0.10
    onium
    0.10
    åĽĽæº¢
    0.09
    ادÙħ
    0.09
    forsk
    0.09
    lomer
    0.09
    ivity
    0.09
    à¯ģ
    0.09
    ively
    0.08
    Activations Density 0.013%

    No Known Activations