© 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. 61108
    Prev
    Next
    INDEX
    Explanations

    statistically significant differences

    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
    ILLE
    -0.08
    verso
    -0.08
    undy
    -0.08
    å¼ıåĴĮ
    -0.08
    ëĭ´
    -0.08
    воло
    -0.08
    .files
    -0.08
    classpath
    -0.08
    posito
    -0.08
    aide
    -0.08
    POSITIVE LOGITS
    ifi
    0.07
    /non
    0.07
     (>
    0.06
     significance
    0.06
    /unit
    0.06
    *
    0.06
    (
    0.06
    ä¸İ伦
    0.06
    mente
    0.06
    ly
    0.06
    Activations Density 0.032%

    No Known Activations