© 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. 13663
    Prev
    Next
    INDEX
    Explanations

    margin, padding, zero

    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
    æĸ°åĬłåĿ¡
    -0.09
    éĩįè¦ģçļĦæĺ¯
    -0.08
    åĬłæĭ¿å¤§
    -0.08
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    -0.08
    enburg
    -0.07
    owitz
    -0.07
    elho
    -0.07
    uolo
    -0.07
    身临åħ¶å¢ĥ
    -0.07
    otle
    -0.07
    POSITIVE LOGITS
    inkin
    0.07
    奢
    0.07
     whatever
    0.06
    whatever
    0.06
    моÑĤ
    0.06
     Syntax
    0.06
    çĦ¶åIJİéĢļè¿ĩ
    0.06
    ÛĮØ´
    0.06
    literal
    0.06
    _identity
    0.06
    Activations Density 0.061%

    No Known Activations