© 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. 38213
    Prev
    Next
    INDEX
    Explanations

    exponents and power laws

    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
    ously
    -0.07
    abox
    -0.07
    aub
    -0.07
    ä½łæĺ¯æĪijçļĦ
    -0.07
    èĢĥè¯ķç½ij
    -0.07
    ONG
    -0.06
    å¾ĢæĿ¥
    -0.06
    egie
    -0.06
    ackage
    -0.06
    _border
    -0.06
    POSITIVE LOGITS
    èijĨ
    0.08
    enity
    0.07
    arate
    0.07
    è²
    0.07
    flatten
    0.07
     empir
    0.07
    è¡ĮèĢħ
    0.07
    %/
    0.07
     flatten
    0.07
    নà§įদ
    0.07
    Activations Density 0.007%

    No Known Activations