© 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. 29220
    Prev
    Next
    INDEX
    Explanations

    image file paths

    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
    .wik
    -0.08
    OOT
    -0.07
    شر
    -0.07
     ÑĢазÑĥ
    -0.07
    æľīä¸Ģå¥Ĺ
    -0.07
    Âł
    -0.07
    å¨Ħ
    -0.06
     wee
    -0.06
    èĩªè¨Ģ
    -0.06
    azi
    -0.06
    POSITIVE LOGITS
    .jpeg
    0.08
    .png
    0.07
    许åı¯æĸĩ件
    0.07
    Untitled
    0.07
    truncate
    0.07
    .jpg
    0.07
    .JPG
    0.07
    chand
    0.07
    åIJĦè¡Įä¸ļ
    0.07
    amentas
    0.07
    Activations Density 0.098%

    No Known Activations