© 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. 19448
    Prev
    Next
    INDEX
    Explanations

    court case citations

    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
    orong
    -0.08
    å°±ä¸ļå½¢åĬ¿
    -0.08
    ãĤ·ãĥ§ãĥĥãĤ¯
    -0.07
    缸åħ³éĺħ读
    -0.07
    eku
    -0.07
    å®ŀéªĮå°ıåѦ
    -0.07
    å¯Ľ
    -0.07
    [table
    -0.07
    encode
    -0.07
    ERTICAL
    -0.07
    POSITIVE LOGITS
    çļĦéĤ£ç§į
    0.07
    aupts
    0.06
     retro
    0.06
    çIJ³å¨ľ
    0.06
    æŬ
    0.06
    åľ°åĪ©
    0.06
    лл
    0.06
    é£
    0.06
     (
    0.06
     Scre
    0.06
    Activations Density 0.291%

    No Known Activations