© 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. 21513
    Prev
    Next
    INDEX
    Explanations

    trust and relationships

    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
    åı¯ä¿¡
    -0.08
    ä¿¡éł¼
    -0.06
     trusted
    -0.06
     ìĭłë¢°
    -0.06
    åı¯éĿł
    -0.06
    ness
    -0.06
     credible
    -0.06
    æĬĬæı¡
    -0.06
    åı¯éĿłçļĦ
    -0.06
    éªĮ
    -0.06
    POSITIVE LOGITS
    athon
    0.07
    اÙĨب
    0.07
    ovre
    0.07
    atorii
    0.06
    ãĤĵãģ³
    0.06
    omorphic
    0.06
    วà¸Ļ
    0.06
    åĹĸ
    0.06
    ancock
    0.06
    inson
    0.06
    Activations Density 0.003%

    No Known Activations