© 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. 17946
    Prev
    Next
    INDEX
    Explanations

    mystery film, novels, creature, box

    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
    uality
    -0.05
     зага
    -0.05
    éļĽ
    -0.05
    ãģ£ãģŁ
    -0.05
    ç½®
    -0.05
    elin
    -0.05
    à°µ
    -0.05
    eries
    -0.05
    éĻħ
    -0.05
    çļĦä¸įåIJĮ
    -0.05
    POSITIVE LOGITS
    ами
    0.08
     dég
    0.06
    byt
    0.06
    èĻ«
    0.06
    lear
    0.06
    udir
    0.06
    ãģªãģ®ãģ¯
    0.06
    ofs
    0.06
    }`).
    0.06
    bler
    0.06
    Activations Density 0.001%

    No Known Activations