© 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. 2083
    Prev
    Next
    INDEX
    Explanations

    command or url

    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
    æ¯Ķå¦Ĥ
    -0.08
    ä¾ĭå¦Ĥ
    -0.08
    æ¯Ķå¦Ĥ说
    -0.08
    ä¾ĭãģĪãģ°
    -0.07
     (<
    -0.07
    apg
    -0.07
     напÑĢимеÑĢ
    -0.07
    hydrate
    -0.06
    اÙĦÙĩ
    -0.06
    ecret
    -0.06
    POSITIVE LOGITS
    ä¸Ĭè¿°
    0.16
     above
    0.16
    ä¸Ĭè¨ĺ
    0.14
    above
    0.13
    Above
    0.13
     Above
    0.13
    ä¸ĬéĿ¢çļĦ
    0.12
     вÑĭÑĪе
    0.12
     acima
    0.12
    åľ¨ä¸Ĭè¿°
    0.11
    Activations Density 0.206%

    No Known Activations