© 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. 49216
    Prev
    Next
    INDEX
    Explanations

    detail.build

    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
    etas
    -0.07
    es
    -0.06
    è®¤çľŁéĺħ读
    -0.06
    osu
    -0.06
    æľĢæĸ°åıijå¸ĥ
    -0.06
    zas
    -0.06
    ose
    -0.06
    os
    -0.06
    esz
    -0.06
    uster
    -0.06
    POSITIVE LOGITS
    RefPtr
    0.09
    '](
    0.07
     Sungai
    0.07
    MouseEvent
    0.07
    AsyncResult
    0.07
    ÙĪزÙĩ
    0.07
    sher
    0.07
    ãĥ¼ãĥł
    0.07
    æģ©
    0.07
    PCODE
    0.07
    Activations Density 0.094%

    No Known Activations