© 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. 22118
    Prev
    Next
    INDEX
    Explanations

    import numpy, pandas, pymc

    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
    agli
    -0.07
    <?>
    -0.07
    è´´çĿĢ
    -0.07
     vit
    -0.06
    agas
    -0.06
    blind
    -0.06
    ime
    -0.06
    !</
    -0.06
    -but
    -0.06
     blind
    -0.06
    POSITIVE LOGITS
    epy
    0.09
    illance
    0.08
    apsed
    0.08
    IDDEN
    0.07
    OLUTE
    0.07
    دÙĬÙĪ
    0.07
    isci
    0.07
    så
    0.07
    otes
    0.07
    æľįåĬ¡æ°´å¹³
    0.07
    Activations Density 0.009%

    No Known Activations