© 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. 41277
    Prev
    Next
    INDEX
    Explanations

    crucial / critical / vital

    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
    :normal
    -0.07
    æīįæĺ¯çľŁæŃ£çļĦ
    -0.07
    主è¦ģåİŁåĽł
    -0.07
    主è¦ģ表çݰ为
    -0.07
    rik
    -0.07
    amax
    -0.07
    гÑĥÑĤ
    -0.07
    verity
    -0.07
    çĶ¨åĬĽ
    -0.07
    æľĢåIJĪéĢĤ
    -0.07
    POSITIVE LOGITS
    çļĦä¸Ģçݯ
    0.10
    issime
    0.09
    ä¸Ģçݯ
    0.08
    ÃŃsima
    0.08
    çĦ¡æ¯Ķ
    0.08
    åĵī
    0.08
    æĬī
    0.08
    çݯèĬĤä¸Ń
    0.08
    ly
    0.08
     ×ij×Ļ×ķתר
    0.08
    Activations Density 0.146%

    No Known Activations