© 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. 19273
    Prev
    Next
    INDEX
    Explanations

    return value

    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
    kaar
    -0.07
     Tops
    -0.07
    VEL
    -0.07
    éĺĻ
    -0.07
    archy
    -0.07
    ppi
    -0.07
    rafe
    -0.07
    obe
    -0.07
    -components
    -0.06
    arrer
    -0.06
    POSITIVE LOGITS
    æİĸ
    0.08
    ä½łçļĦ人
    0.08
    å½¢
    0.08
    ä½łäºĨ
    0.07
    uens
    0.07
    å»Ĭ
    0.07
     Algar
    0.07
    åĬłæĭ¿å¤§
    0.07
    _MA
    0.07
    诣
    0.07
    Activations Density 0.001%

    No Known Activations