© 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. 15598
    Prev
    Next
    INDEX
    Explanations

    file/class prefixes

    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
    ÑĤÑĸ
    -0.07
    -Encoding
    -0.06
    LEMENT
    -0.06
    +xml
    -0.06
    witz
    -0.06
    IGE
    -0.06
    ique
    -0.06
    é½IJå¿ĥ
    -0.06
    åĤį
    -0.06
    èĢĮèĩ³
    -0.06
    POSITIVE LOGITS
    转åĢº
    0.08
    ctl
    0.08
    core
    0.08
    rawd
    0.08
    cms
    0.08
    intern
    0.08
    è¯¥ä½ľèĢħ
    0.08
    prima
    0.07
    æīĢæľīç«łèĬĤ
    0.07
    ÑĢевно
    0.07
    Activations Density 0.501%

    No Known Activations