© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21666
    Prev
    Next
    INDEX
    Explanations

    removing material away

    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
    igre
    -0.08
     Beard
    -0.08
    orque
    -0.08
    .addHandler
    -0.07
    orique
    -0.07
    amin
    -0.07
    éĢıæ°Ķ
    -0.07
    ypi
    -0.06
    UCH
    -0.06
     ìłĪëĮĢ
    -0.06
    POSITIVE LOGITS
    çķĻä¸ĭæĿ¥çļĦ
    0.10
    åıªåī©ä¸ĭ
    0.10
    涤
    0.08
    åıªåī©
    0.08
     leaving
    0.08
    åī©ä¸ĭ
    0.08
    æĿĤ
    0.08
    Coder
    0.08
    éĻ¤æİī
    0.07
    ç§
    0.07
    Activations Density 0.070%

    No Known Activations