© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20400
    Prev
    Next
    INDEX
    Explanations

    . and common endings

    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
    вÑĤÑĢа
    -0.06
    staan
    -0.06
    /TR
    -0.06
    ancier
    -0.06
     fanta
    -0.06
    ำà¸Ļ
    -0.06
    亿人æ°ijå¸ģ
    -0.06
     Freih
    -0.06
    jaz
    -0.06
    idio
    -0.06
    POSITIVE LOGITS
    Pi
    0.05
    ofi
    0.05
    aki
    0.05
    使çĶ¨åīį
    0.05
     gi
    0.05
    sus
    0.05
    æĿ¡
    0.05
    ern
    0.05
    riv
    0.05
    pi
    0.04
    Activations Density 0.075%

    No Known Activations