© 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. 19882
    Prev
    Next
    INDEX
    Explanations

    supporting physical actions

    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
     confron
    -0.07
    alon
    -0.07
    åĿ¤
    -0.06
     ÙħØ·
    -0.06
    isci
    -0.06
     într
    -0.06
    æķĻå·¥
    -0.06
    ofd
    -0.06
    并æıIJ交
    -0.06
    doch
    -0.06
    POSITIVE LOGITS
    路段
    0.05
    amanya
    0.05
    cule
    0.05
    質
    0.05
    ä¸įåłª
    0.05
     dem
    0.05
     coalition
    0.05
    åĪĨ段
    0.05
     status
    0.05
    LAG
    0.05
    Activations Density 0.003%

    No Known Activations