© 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. 20658
    Prev
    Next
    INDEX
    Explanations

    Copyright notices and names

    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
    xis
    -0.07
    ting
    -0.06
    atre
    -0.06
    landa
    -0.06
    ing
    -0.06
    fino
    -0.06
    ney
    -0.06
    çļĦéĩį
    -0.06
    ilter
    -0.06
    ì¹ł
    -0.06
    POSITIVE LOGITS
    erd
    0.07
     usah
    0.06
    éģĵåºľ
    0.05
    indsight
    0.05
    عاÙħÙĦ
    0.05
    ucci
    0.05
    erc
    0.05
    åĮºåİ¿
    0.05
    eres
    0.05
    åĺİ
    0.05
    Activations Density 0.001%

    No Known Activations