© 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. 61403
    Prev
    Next
    INDEX
    Explanations

    class PropertyDescriptor

    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
    elson
    -0.10
    ebes
    -0.09
    estal
    -0.09
    äsch
    -0.09
    æĪIJç«ł
    -0.08
    plevel
    -0.08
    osity
    -0.08
    abble
    -0.08
    çĹĩæĤ£èĢħ
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    POSITIVE LOGITS
    (es
    0.10
    mates
    0.08
    mate
    0.08
    åŃIJéĩĮ
    0.08
    wide
    0.07
    ughter
    0.07
    led
    0.07
    wohl
    0.07
    o
    0.07
    -wide
    0.07
    Activations Density 0.104%

    No Known Activations