© 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. 21870
    Prev
    Next
    INDEX
    Explanations

    king, queen, or royalty

    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
    ANCH
    -0.06
     deser
    -0.06
     elders
    -0.06
    åŁł
    -0.06
    äºĴåĬ©
    -0.06
    สล
    -0.06
     preval
    -0.06
     amm
    -0.06
     communities
    -0.06
    æĶ¯æı´
    -0.06
    POSITIVE LOGITS
    夹å±Ĥ
    0.06
    ä¸ĭ令
    0.06
    ä¸įåĩı
    0.05
     personalmente
    0.05
     captured
    0.05
     Strateg
    0.05
    为åijĺå·¥
    0.05
    iale
    0.05
    ä¿ĺ
    0.05
     exce
    0.05
    Activations Density 0.016%

    No Known Activations