© 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. 16986
    Prev
    Next
    INDEX
    Explanations

    sulfur compounds and cycles

    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
    oj
    -0.06
    er
    -0.06
    eer
    -0.06
    ech
    -0.05
    gar
    -0.05
    es
    -0.05
    ãģĦ
    -0.05
    æ¡£
    -0.05
    atal
    -0.05
    ape
    -0.05
    POSITIVE LOGITS
    lessly
    0.07
    gesamt
    0.07
    æĤ¨å°±åı¯ä»¥
    0.07
    éĥ¨åĪĨæĺ¯
    0.07
    lander
    0.07
    žite
    0.06
    //(
    0.06
    umbed
    0.06
    udur
    0.06
    æĪIJ为åħ¨çIJĥ
    0.06
    Activations Density 0.003%

    No Known Activations