© 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. 26579
    Prev
    Next
    INDEX
    Explanations

    get started, get rid, get you

    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
    以任ä½ķ
    -0.09
    ç§įç§įåİŁåĽł
    -0.08
    ä¸įæĶ¹
    -0.08
    à¹ĥà¸Ķ
    -0.08
    å¤ĸçļĦ
    -0.08
    yal
    -0.08
    RequestMethod
    -0.08
    ä¸įåĢ¦
    -0.08
    rhein
    -0.08
    ненко
    -0.08
    POSITIVE LOGITS
    tings
    0.12
    åĪ°çļĦ
    0.12
    TING
    0.11
     rid
    0.11
    ting
    0.10
    ational
    0.10
    OrCreate
    0.10
    timeofday
    0.09
    chas
    0.09
    ters
    0.09
    Activations Density 0.183%

    No Known Activations