© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11852
    Prev
    Next
    INDEX
    Explanations

    stage, names, sin

    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
    akang
    -0.08
    _nullable
    -0.08
     sogenannte
    -0.07
    prinz
    -0.07
    ä¸įä»ħåľ¨
    -0.07
    ä¼łåªĴæľīéĻIJåħ¬åı¸
    -0.07
    åѦä¸İ
    -0.07
     tzv
    -0.07
    nus
    -0.07
    ä¸įä»ħæľī
    -0.07
    POSITIVE LOGITS
     nor
    0.11
    èĢĮæĺ¯
    0.11
     necessarily
    0.11
     anymore
    0.10
     melainkan
    0.10
     sondern
    0.10
     οÏįÏĦε
    0.09
    หรà¸Ńà¸ģ
    0.09
    è¿Ļä¹Īç®Ģåįķ
    0.09
    èĢĮæĺ¯è¦ģ
    0.08
    Activations Density 0.015%

    No Known Activations