© 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. 3063
    Prev
    Next
    INDEX
    Explanations

    winding, looping, or tortuous shapes

    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
    裸
    -0.09
     tipped
    -0.08
    ä»Ģä¹Īéĥ½ä¸į
    -0.08
     Bare
    -0.07
    tribute
    -0.07
    ummer
    -0.07
    tributes
    -0.07
    å¯¹åľ¨
    -0.07
    槻
    -0.07
    åħĪåıij
    -0.07
    POSITIVE LOGITS
    æĽ²æĬĺ
    0.15
     zig
    0.12
    è¿Ĥ
    0.11
    å¤ļ次
    0.11
     looping
    0.11
     loops
    0.10
    弯路
    0.10
    éĶĻ综
    0.10
    å¤įæĿĤçļĦ
    0.10
    æĿ¥åĽŀ
    0.10
    Activations Density 0.054%

    No Known Activations