© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20773
    Prev
    Next
    INDEX
    Explanations

    symbolism metaphor, horizontal tail, textcolumn, INNER JOIN

    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
    enu
    -0.07
    _Bool
    -0.06
     outf
    -0.06
    æĸ¥
    -0.06
    VERTEX
    -0.06
    -Za
    -0.06
    åį¡ç½Ĺ
    -0.06
    å¹´ä¸ĢåŃ£åº¦
    -0.06
    第ä¸ĢèĬĤ
    -0.06
    çŀĦ
    -0.06
    POSITIVE LOGITS
    åIJİèĢħ
    0.11
    é¹Ĭ
    0.08
     latter
    0.08
     sensit
    0.08
    æĻļäºĨ
    0.08
    第äºĮç±»
    0.07
    è·
    0.07
    ÑĤоÑĢаÑı
    0.07
    åIJİåįĬ
    0.07
    西ç«Ļ
    0.07
    Activations Density 0.145%

    No Known Activations