© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 40359
    Prev
    Next
    INDEX
    Explanations

    gotta read

    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
    åħ·æľī以ä¸ĭ
    -0.08
    ä¸Ģåīij
    -0.08
    æ´¾åıij
    -0.08
    Ïīμα
    -0.08
    vrier
    -0.08
    nows
    -0.07
    _)
    -0.07
    æĶ¾æĿ¾å¿ĥæĥħ
    -0.07
    )prepare
    -0.07
    æŁ¥çľĭåħ¨éĥ¨
    -0.07
    POSITIVE LOGITS
    !).
    0.10
    !),
    0.08
    ethe
    0.07
     enim
    0.07
    ?).
    0.07
     later
    0.07
    izzi
    0.07
     latter
    0.06
    >).
    0.06
     cioè
    0.06
    Activations Density 0.218%

    No Known Activations