© 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. 22107
    Prev
    Next
    INDEX
    Explanations

    SP

    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
    æĹ¢
    -0.06
    æĹ¢ä¸į
    -0.05
    è¿Ļä¸įä»ħ
    -0.05
     auto
    -0.05
    åį³åľ¨
    -0.05
     precedent
    -0.05
    æīįä¸įä¼ļ
    -0.05
     us
    -0.05
    åĩºåıij
    -0.05
    uth
    -0.04
    POSITIVE LOGITS
    hread
    0.07
     confund
    0.06
     abw
    0.06
    ame
    0.06
    kung
    0.06
    intl
    0.06
    æIJ¾
    0.06
    Cancelled
    0.06
    adwal
    0.06
     nues
    0.06
    Activations Density 0.035%

    No Known Activations