© 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. 1059
    Prev
    Next
    INDEX
    Explanations

    example

    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
    ä¸Ģè¾Ī
    -0.07
    -pocket
    -0.07
    åĬŀäºĭ
    -0.07
    èĩ³ä¸Ĭ
    -0.06
     reportedly
    -0.06
    st
    -0.06
    诸å¦Ĥ
    -0.06
    Ø®ÙĦÙĬ
    -0.06
     CAMP
    -0.06
     cavity
    -0.06
    POSITIVE LOGITS
    tese
    0.08
    ä¾ĭåŃIJ
    0.08
    igan
    0.08
     nghiá»ĩm
    0.08
    voorbeeld
    0.08
    vall
    0.08
     ìĺĪ
    0.08
    à¨ĸ
    0.08
     example
    0.07
     exemple
    0.07
    Activations Density 0.005%

    No Known Activations