© 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. 21240
    Prev
    Next
    INDEX
    Explanations

    #define BOOST_

    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
    ine
    -0.06
    urada
    -0.05
    umes
    -0.05
    inu
    -0.05
    ห
    -0.05
    atura
    -0.05
    æ¤
    -0.05
     gr
    -0.05
    UMA
    -0.05
    umed
    -0.05
    POSITIVE LOGITS
    afe
    0.06
    æĿŀ
    0.06
    isco
    0.06
    ä»»ä½ķæŶåĢĻ
    0.06
    ordat
    0.05
    uc
    0.05
    騰
    0.05
     dizzy
    0.05
     Bolt
    0.05
    ä¸ŃéĢļ
    0.05
    Activations Density 0.033%

    No Known Activations