© 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. 42840
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation

    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
    acons
    -0.07
    ikkert
    -0.07
     unrecognized
    -0.07
    جÙħ
    -0.07
    ä»»æĢ¨
    -0.06
    æĦıè¯ĨåĴĮ
    -0.06
    èij±å§ľ
    -0.06
    lech
    -0.06
    _LANG
    -0.06
    蹦蹦
    -0.06
    POSITIVE LOGITS
    ¢
    0.07
    _typ
    0.07
     Horde
    0.07
    åĽ¾çŃī
    0.06
    ï¸İ
    0.06
    мÑĭ
    0.06
    estal
    0.06
    fato
    0.06
    н
    0.06
    egno
    0.06
    Activations Density 0.022%

    No Known Activations