© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19473
    Prev
    Next
    INDEX
    Explanations

    references with brackets

    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
    çľĭèµ·æĿ¥å¾Ī
    -0.06
    ochond
    -0.06
    -0.05
    мей
    -0.05
    \_
    -0.05
    ä»ĩ
    -0.05
    Ñĥг
    -0.05
    hopefully
    -0.05
    濯
    -0.05
    ouch
    -0.05
    POSITIVE LOGITS
    -none
    0.06
    ÙIJÙħ
    0.06
    imun
    0.06
    ëĭĻ
    0.06
     bik
    0.06
    ç²īç¬Ķ
    0.06
    upun
    0.05
    #{
    0.05
    aisons
    0.05
     bunÄĥ
    0.05
    Activations Density 0.004%

    No Known Activations