© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12066
    Prev
    Next
    INDEX
    Explanations

    ) followed by technical terms

    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
    Ø©
    -0.13
    <|box_end|>
    -0.09
    stime
    -0.07
    åľ°å®ĮæĪIJ
    -0.07
    atched
    -0.07
    ä¸įåı¯éģ¿åħįåľ°
    -0.07
    à¤Ĥह
    -0.07
    ÙħÙĪÙĦ
    -0.07
    /XMLSchema
    -0.07
    stery
    -0.07
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.07
    ios
    0.07
    os
    0.06
    оÑĩки
    0.06
    iod
    0.06
    æĸ°åĬłåĿ¡
    0.06
    um
    0.06
    iology
    0.06
    athi
    0.06
     aufgeh
    0.06
    Activations Density 0.002%

    No Known Activations