© 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. 27283
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with punctuation

    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
     Cass
    -0.06
    au
    -0.06
    ↵
    -0.06
    tera
    -0.06
    ξε
    -0.06
    ual
    -0.06
     cass
    -0.05
    >');
    -0.05
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.05
    up
    -0.05
    POSITIVE LOGITS
    åŃIJæĽ°
    0.10
    ogie
    0.09
    ustum
    0.09
    ðŁĺī
    0.09
    EventArgs
    0.08
     openid
    0.08
    ç¼ĸçīĪ
    0.08
    irit
    0.08
    ementer
    0.08
    endenza
    0.08
    Activations Density 0.011%

    No Known Activations