© 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. 17547
    Prev
    Next
    INDEX
    Explanations

    the majority

    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
    hall
    -0.06
     hal
    -0.05
    cut
    -0.05
    好好çļĦ
    -0.05
    hal
    -0.05
    μά
    -0.05
    LESS
    -0.05
    ä¸įåĬł
    -0.05
    æģ¢å¤įæŃ£å¸¸
    -0.05
    æĭĵ宽
    -0.05
    POSITIVE LOGITS
     enough
    0.06
    bourne
    0.06
     whe
    0.05
    blig
    0.05
    anker
    0.05
    ç»ĦæĪIJ
    0.05
    循çݯç»ıæµİ
    0.05
     اÙĦÚ©
    0.05
    åIJŀåIJIJ
    0.05
    Enough
    0.05
    Activations Density 0.001%

    No Known Activations