© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 40985
    Prev
    Next
    INDEX
    Explanations

    general

    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
    egram
    -0.08
    -bre
    -0.08
    Bre
    -0.08
    ropol
    -0.07
    侥幸
    -0.07
    çĹħåѦ
    -0.07
    çļĦä¸ĵä¸ļ
    -0.07
    åĥļ
    -0.07
    èŃľ
    -0.07
    hani
    -0.07
    POSITIVE LOGITS
    åıĬåIJĦ
    0.12
    åĴĮåIJĦ
    0.11
     generale
    0.10
    inet
    0.10
    /general
    0.09
    general
    0.09
    éĢļç͍çļĦ
    0.09
    eneral
    0.09
    åıĬåIJĦç§į
    0.09
    éĢļç͍
    0.09
    Activations Density 0.640%

    No Known Activations