© 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. 58745
    Prev
    Next
    INDEX
    Explanations

    hot or warm drinks

    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
    åĽłä¸ºæľīäºĨ
    -0.08
     Darling
    -0.07
    lobals
    -0.07
    èī°éļ¾
    -0.07
    ç®Ģåįķæĺĵ
    -0.07
    agnol
    -0.06
    å¿łå¿ĥ
    -0.06
    åĶ¯
    -0.06
     ReturnType
    -0.06
    让èĩªå·±çļĦ
    -0.06
    POSITIVE LOGITS
     freshly
    0.13
     fresh
    0.11
    fresh
    0.11
    æĸ°é²ľçļĦ
    0.11
    สà¸Ķ
    0.10
     freshness
    0.10
    åĪļä»İ
    0.10
     Fresh
    0.10
    Fresh
    0.10
     frisch
    0.09
    Activations Density 0.096%

    No Known Activations