© 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. 46313
    Prev
    Next
    INDEX
    Explanations

    grid placement and shapes

    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
    dü
    -0.08
    ä¿ĿçķĻ
    -0.07
     lug
    -0.07
     Bour
    -0.07
    alie
    -0.07
    ä¸įæĸŃå¢ŀåĬł
    -0.07
    çĤ¼
    -0.06
    usen
    -0.06
     lim
    -0.06
    渣
    -0.06
    POSITIVE LOGITS
    ettes
    0.08
    ìĬ¤íĦ°
    0.08
    æĢ»éĿ¢ç§¯
    0.08
    SCII
    0.08
     orientations
    0.08
    -placement
    0.07
    ä¹ĭéķ¿
    0.07
     oriented
    0.07
    tiles
    0.07
     orientation
    0.07
    Activations Density 0.005%

    No Known Activations