© 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. 16942
    Prev
    Next
    INDEX
    Explanations

    breeding systems, models, design

    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
    为æŃ¢
    -0.06
    åĪĨ解
    -0.06
    æĸ¹æ³ķ
    -0.05
    ä¹Ŀ
    -0.05
    occasion
    -0.05
    å·¥ä½ľ
    -0.05
     subtil
    -0.05
    å¤į
    -0.05
     method
    -0.05
    ç»ĵ
    -0.05
    POSITIVE LOGITS
     mal
    0.07
    รั
    0.06
    ãĥ¡ãĥªãĥĥãĥĪ
    0.06
    æĪĸå¤ļ
    0.06
    åħ¨éĿ¢å»ºæĪIJ
    0.06
    unned
    0.06
    بÙĨ
    0.06
    æĪijä¸įç¦ģ
    0.06
    å¤ļè§ģäºİ
    0.06
    ếm
    0.06
    Activations Density 0.039%

    No Known Activations