© 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. 28944
    Prev
    Next
    INDEX
    Explanations

    R and S configurations

    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
    æĤ
    -0.07
    ç®Ĺä¸įä¸Ĭ
    -0.07
    ר×ķת
    -0.07
    ecs
    -0.07
    %c
    -0.07
    åŀ¢
    -0.06
    çĹĶçĸ®
    -0.06
    شت
    -0.06
    ç±»æ¯Ķ
    -0.06
    ecker
    -0.06
    POSITIVE LOGITS
    èĶĶ
    0.07
    atezza
    0.07
    çĽ¸çº¦
    0.07
    umlu
    0.07
    ä¸Ģèĩ´
    0.07
    ä¸Ģèĩ´çļĦ
    0.06
    ä»ĩ
    0.06
    ungsweise
    0.06
    ChildIndex
    0.06
    orman
    0.06
    Activations Density 0.097%

    No Known Activations