© 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. 18374
    Prev
    Next
    INDEX
    Explanations

    physical activity and movement

    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
    æīįè¡Į
    -0.07
    ynn
    -0.07
    æīģ
    -0.07
    pliant
    -0.07
    oksi
    -0.06
    æīĢè¬Ĥ
    -0.06
    astically
    -0.06
    vy
    -0.06
    æĪĸå¤ļ个
    -0.06
    çļĦ家ä¼Ļ
    -0.06
    POSITIVE LOGITS
     pag
    0.05
    registr
    0.05
    st
    0.05
    ä¸Ģ段
    0.05
     letter
    0.05
    SQ
    0.04
    æ¯ıåħ¬æĸ¤
    0.04
    imb
    0.04
    SCALL
    0.04
    åľ
    0.04
    Activations Density 0.001%

    No Known Activations