© 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. 11638
    Prev
    Next
    INDEX
    Explanations

    facing directions

    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
     slog
    -0.07
    åĪ°åĵªéĩĮ
    -0.07
     estim
    -0.07
    volu
    -0.07
    累积
    -0.07
    smooth
    -0.06
    æĬ±åĽ¢
    -0.06
    åĮħéĩĮ
    -0.06
    å¥Ķèµ°
    -0.06
    oyo
    -0.06
    POSITIVE LOGITS
    éĿ¢åIJij
    0.09
     convention
    0.09
    è§Ĥçľĭ
    0.09
    orex
    0.09
    -facing
    0.09
     viewer
    0.08
    éĿ¢å¯¹éĿ¢
    0.08
    orient
    0.08
     orientation
    0.08
     menghad
    0.08
    Activations Density 0.013%

    No Known Activations