© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32994
    Prev
    Next
    INDEX
    Explanations

    call to action / visit / book

    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
    U
    -0.08
    åĽ´ç»ķ
    -0.08
     usual
    -0.08
    åĩŃ
    -0.07
    åľĪ
    -0.07
    uttle
    -0.06
    强è°ĥäºĨ
    -0.06
    H
    -0.06
    etas
    -0.06
    ç¯ĩä¸Ģ
    -0.06
    POSITIVE LOGITS
    ÑĢÑĭз
    0.08
    /licenses
    0.08
    /span
    0.08
    èľĪ
    0.08
    ,'\
    0.08
    akra
    0.07
    aeda
    0.07
    Æł
    0.07
    ,//
    0.07
    ulik
    0.07
    Activations Density 0.001%

    No Known Activations