© 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. 45967
    Prev
    Next
    INDEX
    Explanations

    InputStream, Reader, Stream

    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
    æµ®
    -0.07
    omics
    -0.07
    uns
    -0.06
    боÑĢо
    -0.06
    imo
    -0.06
    ween
    -0.06
    绿
    -0.06
    åįĬè¾¹
    -0.06
    ç²¾ç¥ŀ
    -0.06
    ä¹ĺ
    -0.06
    POSITIVE LOGITS
    icer
    0.09
    semble
    0.08
    ä¸Ģå¹´åĽĽåŃ£
    0.08
    дÑĢÑı
    0.08
     ÑĥÑģÑĤÑĢойÑģÑĤва
    0.08
     irm
    0.08
    ibert
    0.08
    è¸ıè¸ıå®ŀ
    0.07
    ostante
    0.07
    edin
    0.07
    Activations Density 0.002%

    No Known Activations