© 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. 17312
    Prev
    Next
    INDEX
    Explanations

    some followed by noun

    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
    cpy
    -0.06
    jek
    -0.06
    uild
    -0.06
    æ¯Ļ
    -0.06
    aring
    -0.06
    itz
    -0.05
    usage
    -0.05
    zek
    -0.05
     دÙĦ
    -0.05
    çĿĽ
    -0.05
    POSITIVE LOGITS
    ecke
    0.05
    ered
    0.05
    eru
    0.05
    人家
    0.05
     اÙĦÙħÙĥر
    0.05
    æĥ¯äºĨ
    0.05
    ifo
    0.05
     Aston
    0.05
    leden
    0.05
    øn
    0.05
    Activations Density 0.065%

    No Known Activations