© 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. 55574
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     se
    -0.06
    çľŁä¼ª
    -0.06
    ó
    -0.06
    turut
    -0.06
    elage
    -0.06
    ìĦ¤
    -0.06
    æŶä¸įæŶ
    -0.06
    atta
    -0.06
    tran
    -0.06
    apus
    -0.06
    POSITIVE LOGITS
    bsp
    0.08
    cato
    0.08
    代çIJĨ
    0.07
    agni
    0.07
    vain
    0.07
    _escape
    0.07
    uyo
    0.07
    å¤ļ大
    0.07
    ·
    0.07
    ücke
    0.07
    Activations Density 0.080%

    No Known Activations