© 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. 39904
    Prev
    Next
    INDEX
    Explanations

    ; ) . code delimiters

    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
    ãģĻãģĮ
    -0.07
    ãģ£ãģįãĤĬ
    -0.06
    ä¸´æ±Ł
    -0.06
    TROD
    -0.06
    åıijåĩºçļĦ
    -0.06
    å¼ĤçļĦ
    -0.06
    æ½ĩæ¹ĺ
    -0.06
    ĩ
    -0.06
    à¸Ķย
    -0.06
    è¿ĩç¥ŀ
    -0.06
    POSITIVE LOGITS
    winkel
    0.08
    utto
    0.07
    ç¯ĩ
    0.07
    engen
    0.06
    owl
    0.06
    ovo
    0.06
     buttonText
    0.06
     sne
    0.06
    èĢĮçŁ¥
    0.06
    uts
    0.06
    Activations Density 0.370%

    No Known Activations