© 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. 16687
    Prev
    Next
    INDEX
    Explanations

    room

    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
     obsta
    -0.10
    è¿ŀäºij
    -0.09
    +":
    -0.09
    :request
    -0.09
    ---</
    -0.08
     particol
    -0.08
    onomia
    -0.08
    åħ³äºİæĪij们
    -0.08
    åĪ«è¯´
    -0.08
    еÑĤка
    -0.08
    POSITIVE LOGITS
    æĪĸ
    0.06
     or
    0.06
    ,
    0.06
    0.06
    chow
    0.05
     (
    0.05
    ä¸Ģ
    0.05
     qu
    0.05
    æĪĸèĢħæĺ¯
    0.05
    /
    0.05
    Activations Density 1.132%

    No Known Activations