© 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. 56127
    Prev
    Next
    INDEX
    Explanations

    select SUBSTRING

    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
    udin
    -0.07
    æĽľ
    -0.07
    imple
    -0.07
    cad
    -0.07
    ä¹ĭéķ¿
    -0.06
    ewel
    -0.06
    jt
    -0.06
     khẩu
    -0.06
    èĩªå·±åĬ¨æīĭ
    -0.06
    коÑĢи
    -0.06
    POSITIVE LOGITS
    rensa
    0.08
    romium
    0.08
    inals
    0.08
    ******/
    0.07
     جاÙĩ
    0.07
    anges
    0.07
    åľ¨è§Ħå®ļ
    0.07
    egner
    0.07
     herv
    0.07
    heck
    0.07
    Activations Density 0.034%

    No Known Activations