© 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. 61426
    Prev
    Next
    INDEX
    Explanations

    research & therapy

    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
    uccio
    -0.09
    asco
    -0.08
    cuit
    -0.08
    à¤Ĺा
    -0.07
    erras
    -0.07
    blatt
    -0.07
    åĴ¨è¯¢
    -0.07
    uess
    -0.07
    iras
    -0.07
     Nen
    -0.07
    POSITIVE LOGITS
    å¼ĢæºIJ
    0.07
     openness
    0.07
    ?url
    0.06
    å¹³åı°ä¸Ĭ
    0.06
    ouv
    0.06
    earable
    0.06
     unic
    0.06
     crowdfunding
    0.06
    live
    0.06
     http
    0.06
    Activations Density 0.397%

    No Known Activations