© 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. 15336
    Prev
    Next
    INDEX
    Explanations

    next child ID destination

    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
    gar
    -0.08
    ils
    -0.07
    ilu
    -0.07
    ombs
    -0.07
    urs
    -0.07
    Gar
    -0.07
    çľĭçĿĢ
    -0.07
    /rules
    -0.07
     anch
    -0.07
    letics
    -0.07
    POSITIVE LOGITS
    æĽ´è¿ľ
    0.10
    ä¸įè¿ľ
    0.08
    ä¸ĭä¸Ģç¯ĩ
    0.08
    è·ĿéĽ¢
    0.08
    缸éĤ»
    0.08
     neighboring
    0.07
    å¤ªè¿ľ
    0.07
     nextPage
    0.07
     neighbouring
    0.07
    ä¸ĭä¸Ģ级
    0.07
    Activations Density 0.025%

    No Known Activations