© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19078
    Prev
    Next
    INDEX
    Explanations

    regardless of

    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
    å·´å·´
    -0.05
    èĢĮåľ¨
    -0.05
    è´µçļĦ
    -0.05
    èĢĮå¦Ĥæŀľ
    -0.05
    egen
    -0.05
    éģ¥éģ¥
    -0.05
    èĢĮè¿Ļ个
    -0.05
    åľ¨ä»¥
    -0.05
    å°ijäºİ
    -0.05
     refer
    -0.05
    POSITIVE LOGITS
    ptos
    0.06
    ÑĭÑĢ
    0.06
    åı¯æĥ³
    0.06
    ár
    0.05
    æľ¬èº«çļĦ
    0.05
    erd
    0.05
    inka
    0.05
    /library
    0.05
    -comp
    0.05
    uts
    0.05
    Activations Density 0.004%

    No Known Activations