© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21312
    Prev
    Next
    INDEX
    Explanations

    searching, selecting, applications, develop, research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    个æĪĸå¤ļ个
    -0.06
    éĢļ常æĺ¯
    -0.06
     usually
    -0.06
    usually
    -0.06
     Usually
    -0.06
    人æ°ijèŃ¦å¯Ł
    -0.06
     sometimes
    -0.05
    å¾Ģå¾Ģ
    -0.05
     yourself
    -0.05
    Glob
    -0.05
    POSITIVE LOGITS
    æľīæѤ
    0.06
     aforementioned
    0.06
    åĪĿæŃ¥
    0.06
     doÄŁr
    0.06
    æŃ¤é¡¹
    0.06
    æĸ°çļĦ
    0.05
     żyw
    0.05
    æľ¬æ¡Ī
    0.05
    ä¸įå°ijäºİ
    0.05
    æѤä¸Ģ
    0.05
    Activations Density 0.006%

    No Known Activations