© 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. 50145
    Prev
    Next
    INDEX
    Explanations

    either/or

    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
    çݯä¿Ŀç§ijæĬĢæľīéĻIJåħ¬åı¸
    -0.07
    .unlink
    -0.07
    æĸĮ
    -0.07
    orado
    -0.07
    (:,:,
    -0.07
    zcze
    -0.06
    vorm
    -0.06
    icut
    -0.06
    åĭķæħĭ
    -0.06
    éľīèıĮ
    -0.06
    POSITIVE LOGITS
    累计
    0.09
     interle
    0.08
    èij
    0.08
    æĢ»åħ±
    0.07
     increments
    0.07
    ä¸įéĻIJ
    0.07
    äº¤æĽ¿
    0.07
     cumulative
    0.07
    夹æĿĤ
    0.07
     пеÑĢеме
    0.07
    Activations Density 0.002%

    No Known Activations