© 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. 62094
    Prev
    Next
    INDEX
    Explanations

    http URLs

    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
    lave
    -0.08
    ðŁĻĤ
    -0.08
    обе
    -0.08
    imals
    -0.08
    åŃIJæĽ°
    -0.08
    flix
    -0.08
    <|box_end|>
    -0.08
    veli
    -0.07
    unnable
    -0.07
    apter
    -0.07
    POSITIVE LOGITS
    %
    0.06
    =
    0.06
    wah
    0.06
     correctly
    0.06
    zz
    0.06
    æĦĪ
    0.06
     Ev
    0.06
    '
    0.05
    /
    0.05
    çĿĢæĥ³
    0.05
    Activations Density 0.161%

    No Known Activations