© 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. 43985
    Prev
    Next
    INDEX
    Explanations

    -intensive

    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
     viá»ĩn
    -0.08
    pire
    -0.08
    oseb
    -0.08
    iefert
    -0.07
    åıĸç»ı
    -0.07
     Pellegr
    -0.07
    roda
    -0.07
    sak
    -0.07
    itto
    -0.07
    ialog
    -0.07
    POSITIVE LOGITS
    ä¸Ķåħ·æľī
    0.12
    ä¸Ķæľī
    0.10
    ä¸Ķ
    0.10
     ones
    0.09
    ä¸Ķä¸į
    0.09
    诸å¦Ĥ
    0.09
    ä¸Ķåľ¨
    0.08
     вÑĢоде
    0.08
    èİ«è¿ĩäºİ
    0.08
    ä¾ĭå¦Ĥ
    0.08
    Activations Density 0.062%

    No Known Activations