© 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. 12427
    Prev
    Next
    INDEX
    Explanations

    terms of license and conditions

    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
    ়
    -0.09
    缸è¾ħ缸æĪIJ
    -0.08
    estate
    -0.08
    à¸Ķà¹Į
    -0.08
    а
    -0.08
    ÙĥÙħØ©
    -0.07
    s
    -0.07
    urator
    -0.07
    ftware
    -0.07
    erman
    -0.07
    POSITIVE LOGITS
    inals
    0.15
    perature
    0.12
    olecular
    0.10
    aceous
    0.10
    lessly
    0.10
    wise
    0.10
    inal
    0.09
    arz
    0.09
    (s
    0.09
    atively
    0.08
    Activations Density 0.042%

    No Known Activations