© 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. 20144
    Prev
    Next
    INDEX
    Explanations

    parenthetical 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
     exercises
    -0.07
    jang
    -0.07
    ostas
    -0.07
    äh
    -0.07
    immel
    -0.07
    anes
    -0.06
    ovic
    -0.06
    áp
    -0.06
    WindowTitle
    -0.06
    è¡Į使
    -0.06
    POSITIVE LOGITS
    æīĢçŁ¥
    0.07
    porte
    0.07
     ere
    0.07
    èĥ½çĶ¨
    0.07
    onti
    0.07
    请çĶ¨
    0.06
     sto
    0.06
    ä¸įæ±Ĥ
    0.06
     Apare
    0.06
    apo
    0.06
    Activations Density 0.003%

    No Known Activations