© 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. 4531
    Prev
    Next
    INDEX
    Explanations

    modal dialogs

    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
    ä½ľåģĩ
    -0.08
    itemap
    -0.07
    öll
    -0.07
     slog
    -0.07
     onDataChange
    -0.07
    enet
    -0.07
     petr
    -0.07
     symb
    -0.06
    ropol
    -0.06
     extrapol
    -0.06
    POSITIVE LOGITS
    çªĹåı£
    0.09
    duration
    0.09
     duration
    0.09
    å½Ī
    0.09
    _DURATION
    0.08
     modal
    0.08
     Duration
    0.08
    对è¯Ŀæ¡Ĩ
    0.08
    modal
    0.08
    Duration
    0.08
    Activations Density 0.264%

    No Known Activations