© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 747
    Prev
    Next
    INDEX
    Explanations

    used to, habit, conditioned

    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
    Negative Logits
     anonymously
    -0.07
    rava
    -0.07
     UND
    -0.07
    inker
    -0.07
    unky
    -0.07
    imba
    -0.07
    è¯Ĺæĥħ
    -0.07
    prox
    -0.07
    ughs
    -0.06
    并å¤Ħ
    -0.06
    POSITIVE LOGITS
    ä¹łæĥ¯äºĨ
    0.16
    ä¹łæĥ¯
    0.14
     habit
    0.14
     пÑĢивÑĭ
    0.14
    ç¿Ĵæħ£
    0.13
    ä¹ł
    0.13
    ä¹łæĥ¯æĢ§
    0.13
    ä¹łæĥ¯äºİ
    0.13
     Habit
    0.12
    çļĦä¹łæĥ¯
    0.12
    Activations Density 0.206%

    No Known Activations