© 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. 22477
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    /uploads
    -0.07
     ode
    -0.07
    æĿ¾
    -0.06
    stras
    -0.06
    sic
    -0.06
    ñera
    -0.06
    oris
    -0.06
    ennie
    -0.06
    jac
    -0.06
     stresses
    -0.06
    POSITIVE LOGITS
    åIJİæīį
    0.08
     Paz
    0.07
    æĿĨèıĮ
    0.07
    ä¸į欲
    0.07
    èĢĮä¸įè§ģ
    0.07
    enges
    0.07
    èIJ¥éĢłèī¯å¥½
    0.07
     followed
    0.07
    isco
    0.07
    åIJİæľī
    0.07
    Activations Density 0.010%

    No Known Activations