© 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. 50155
    Prev
    Next
    INDEX
    Explanations

    following lists

    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
     tslint
    -0.08
    æĿ¥çļĦ
    -0.08
    æĥ³æĿ¥
    -0.08
     angef
    -0.08
    coming
    -0.08
    ylon
    -0.08
    sein
    -0.08
    arness
    -0.07
    foundland
    -0.07
    hoff
    -0.07
    POSITIVE LOGITS
    0.08
    æĹ
    0.06
    ä½łçļĦæľĭåıĭ
    0.06
    AMI
    0.06
    caa
    0.06
    Lim
    0.06
    綿
    0.05
     sw
    0.05
     summers
    0.05
     Attr
    0.05
    Activations Density 2.708%

    No Known Activations