© 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. 47664
    Prev
    Next
    INDEX
    Explanations

    task requirement or exercise

    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
    loquent
    -0.08
    hon
    -0.07
    itudes
    -0.07
    稳
    -0.07
    _EDITOR
    -0.07
    idges
    -0.07
    irman
    -0.07
    hen
    -0.06
    Idle
    -0.06
     Buon
    -0.06
    POSITIVE LOGITS
    åİŁé¢ĺ
    0.07
    åİŁæľ¬æĺ¯
    0.07
     réc
    0.07
    posed
    0.07
    urin
    0.07
    è¦ģæ±Ĥè¿Ľè¡Į
    0.06
    -style
    0.06
    новÑĢемен
    0.06
    سازÛĮ
    0.06
    åľ¨ä¸ĸ
    0.06
    Activations Density 0.002%

    No Known Activations