© 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. 9557
    Prev
    Next
    INDEX
    Explanations

    iPhone or school championship

    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
    éĿĸ
    -0.06
    Reducers
    -0.06
    åĤ¢
    -0.06
    amus
    -0.06
    ä¸ŃçĶŁ
    -0.06
    mund
    -0.06
    ä»ĬæľĿ
    -0.06
    便è¦ģ
    -0.06
    moil
    -0.06
    ç»®
    -0.06
    POSITIVE LOGITS
    á»ģm
    0.08
    empre
    0.08
    ux
    0.08
    å¦Ĥä¸Ĭ
    0.07
    çľģéķ¿
    0.07
    euse
    0.07
    usat
    0.07
    足以
    0.07
    è¡ĢçĹĩ
    0.07
    第ä¸Ģè´¢ç»ı
    0.07
    Activations Density 0.015%

    No Known Activations