© 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. 17095
    Prev
    Next
    INDEX
    Explanations

    à¸ĭึà¹Īà¸ĩà¹Ģà¸Ľà¹ĩà¸Ļ

    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
    شار
    -0.06
    ITE
    -0.05
     Ho
    -0.05
    ites
    -0.05
    éģ¥
    -0.05
     agon
    -0.05
    _cast
    -0.05
    gew
    -0.04
     &
    -0.04
     ho
    -0.04
    POSITIVE LOGITS
    à¸ĭึà¹Īà¸ĩà¹Ģà¸Ľà¹ĩà¸Ļ
    0.09
    —the
    0.09
     à¸ĭึà¹Īà¸ĩà¹Ģà¸Ľà¹ĩà¸Ļ
    0.08
    åį³éĢĿ
    0.07
    ä¸įæĦ§æĺ¯
    0.07
    —which
    0.07
    表示
    0.06
     representing
    0.06
    éĤ£åı¯æĺ¯
    0.06
    insky
    0.06
    Activations Density 0.456%

    No Known Activations