© 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. 27354
    Prev
    Next
    INDEX
    Explanations

    menu options and choices

    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
    补缺
    -0.08
     span
    -0.07
    ç¦Ħ
    -0.06
    çĶŁäº§è¿ĩç¨ĭä¸Ń
    -0.06
    Span
    -0.06
    oodoo
    -0.06
    ütt
    -0.06
    scri
    -0.06
    tuj
    -0.06
    åĩºäº§
    -0.06
    POSITIVE LOGITS
     Quit
    0.09
    .Exit
    0.09
    /tty
    0.09
    .quit
    0.08
    .choice
    0.08
     option
    0.08
    éĢĢåĩº
    0.08
     menu
    0.08
    choice
    0.08
    (EXIT
    0.08
    Activations Density 0.094%

    No Known Activations