© 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. 14480
    Prev
    Next
    INDEX
    Explanations

    computing powers and assignments

    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
    æĵ¦
    -0.08
    -components
    -0.07
    汶
    -0.07
    orex
    -0.07
    Margin
    -0.07
    ä¿Ŀå§Ĩ
    -0.07
    èīº
    -0.07
     Äijá»ĵi
    -0.07
     Margin
    -0.07
    ixture
    -0.07
    POSITIVE LOGITS
     powers
    0.10
     factorial
    0.09
    powers
    0.08
     Powers
    0.08
    ụt
    0.08
    åĢįæķ°
    0.08
    uations
    0.07
    åĢįå¢ŀ
    0.07
    fors
    0.07
    è¿IJçĶ¨åĪ°
    0.07
    Activations Density 0.005%

    No Known Activations