© 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. 17812
    Prev
    Next
    INDEX
    Explanations

    work with others

    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
    æł·çļĦ
    -0.06
    款çļĦ
    -0.06
    è¿ĩéĩį
    -0.05
    MDB
    -0.05
    mvc
    -0.05
    æĹłæ¯Ĵ
    -0.05
    ECK
    -0.05
    æľĢ好çļĦ
    -0.05
    brook
    -0.05
     LLC
    -0.05
    POSITIVE LOGITS
    èĩªå·±è¢«
    0.06
    apid
    0.06
    érie
    0.06
    ius
    0.06
    ersi
    0.06
    eno
    0.06
    epak
    0.06
    太平
    0.06
    Tree
    0.05
    æ´»äºĨ
    0.05
    Activations Density 0.005%

    No Known Activations