© 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. 61286
    Prev
    Next
    INDEX
    Explanations

    convex, linear, monotonic, Jensen

    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
     mism
    -0.07
    åĪĨæµģ
    -0.07
    èĵĸ
    -0.07
    å¿ĥç³»
    -0.07
    èļ¤
    -0.07
    INUE
    -0.07
    åĨĴçĿĢ
    -0.07
    åĮ¹éħį
    -0.07
     Somebody
    -0.07
     brav
    -0.07
    POSITIVE LOGITS
     convex
    0.11
    ôs
    0.07
    onis
    0.07
    åĩ¸
    0.07
     ep
    0.07
    -linear
    0.07
     conc
    0.07
     monot
    0.07
    ยิà¹Īà¸ĩ
    0.06
     Jensen
    0.06
    Activations Density 0.006%

    No Known Activations