© 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. 9309
    Prev
    Next
    INDEX
    Explanations

    surface area

    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
     mir
    -0.07
    å®īåħ¨éĺ²èĮĥ
    -0.07
    _dat
    -0.07
    SourceType
    -0.07
    .TypeOf
    -0.07
    igr
    -0.07
    æºIJåľ°
    -0.07
    è¸ıçĿĢ
    -0.06
     Workplace
    -0.06
    -disable
    -0.06
    POSITIVE LOGITS
    表éĿ¢ç§¯
    0.11
    æĢ»éĿ¢ç§¯
    0.10
     surface
    0.09
     ìłijì´ī
    0.09
    éĿ¢ç§¯çļĦ
    0.09
     повеÑĢÑħноÑģÑĤи
    0.09
     surfaces
    0.09
    éĿ¢ç§¯
    0.09
    surface
    0.08
    éĿ¢ç©į
    0.08
    Activations Density 0.015%

    No Known Activations