© 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. 7518
    Prev
    Next
    INDEX
    Explanations

    two or more

    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
    åħ·æľī以ä¸ĭ
    -0.09
    è¿Ŀåıįä¸Ĭè¿°
    -0.08
    رج
    -0.08
    اÙħر
    -0.08
    _singleton
    -0.08
    auft
    -0.08
    _fatal
    -0.08
    çIJ³å¨ľ
    -0.08
    åıĤåĬłåŁ¹è®Ń
    -0.08
    itoris
    -0.07
    POSITIVE LOGITS
    äºĮæĺ¯
    0.08
    ","
    0.07
    elter
    0.07
    '),('
    0.07
    \",\"
    0.07
     ÑģобÑģÑĤвенно
    0.07
    ','
    0.07
    ï¼īãĢģ
    0.06
    )ãĢģ
    0.06
     itself
    0.06
    Activations Density 0.077%

    No Known Activations