© 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. 7623
    Prev
    Next
    INDEX
    Explanations

    note, noting

    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
    rens
    -0.08
    ä½łåij¢
    -0.08
    iber
    -0.08
    ansion
    -0.07
    èĥ½åĬ¨
    -0.07
    åĩĨç¡®çİĩ
    -0.07
    rene
    -0.07
     ÙĩÙħÛĮÙĨ
    -0.07
    igne
    -0.07
    nable
    -0.07
    POSITIVE LOGITS
    ä¹ĭçĶ¨
    0.07
    åIJįæĢĿ
    0.07
    appeared
    0.07
    appe
    0.07
    Overrides
    0.06
    Ł
    0.06
    è¡¥çŁŃ
    0.06
    è¿ijåľ¨
    0.06
    æĶ¶èĹıæľ¬ç«Ļ
    0.06
     Overrides
    0.06
    Activations Density 0.005%

    No Known Activations