© 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. 44076
    Prev
    Next
    INDEX
    Explanations

    fellow called

    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
    æĶ»
    -0.08
    è·¯è¿ĩ
    -0.07
    éĢ¼è¿ij
    -0.07
    å°Ķåħĭ
    -0.07
    ÃĶN
    -0.06
    è¡Įèĩ³
    -0.06
     infiltr
    -0.06
    ä¸įèĥ½å®Įåħ¨
    -0.06
    èĬĬ
    -0.06
    åĪĴè¿ĩ
    -0.06
    POSITIVE LOGITS
     welcoming
    0.16
    æİ¥å¾ħ
    0.16
    欢è¿İ
    0.16
    è¿İæİ¥
    0.16
    è¿İ
    0.15
     welcome
    0.14
    à¸ķà¹īà¸Ńà¸Ļรัà¸ļ
    0.14
     accueill
    0.13
    æŃ¡è¿İ
    0.13
     welcomes
    0.13
    Activations Density 0.383%

    No Known Activations