© 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. 3020
    Prev
    Next
    INDEX
    Explanations

    spaces or language measurement

    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
    è·Ľ
    -0.08
    ä»ħæѤ
    -0.08
    éĩİèĽ®
    -0.07
    æĭĻ
    -0.07
    edur
    -0.07
    èĢĮåĸ»
    -0.07
    æĺĵäºİ
    -0.07
    ียà¸ĩ
    -0.07
    PCODE
    -0.07
    æľīéĻIJçļĦ
    -0.07
    POSITIVE LOGITS
     sophisticated
    0.12
    æ¯Ķè¾ĥå¤įæĿĤ
    0.10
    å¤įæĿĤçļĦ
    0.10
     complexity
    0.10
    çŃīä¸ĵä¸ļ
    0.10
    å¤įæĿĤ
    0.09
     nerd
    0.09
     complex
    0.09
     geek
    0.09
     advanced
    0.09
    Activations Density 0.162%

    No Known Activations