© 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. 17473
    Prev
    Next
    INDEX
    Explanations

    job role or position

    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
     hitch
    -0.06
     impér
    -0.06
    ÑĪла
    -0.06
    legs
    -0.06
    unik
    -0.06
    olist
    -0.06
    æ¯ķèĬĤ
    -0.06
    æĸ¹æ³ķæĿ¥
    -0.06
    ria
    -0.05
    çIJĨäºĭéķ¿
    -0.05
    POSITIVE LOGITS
    iddy
    0.06
     пÑĢедполага
    0.06
    erland
    0.05
     dame
    0.05
    prox
    0.05
    ç»ıæµİæĬĢæľ¯
    0.05
     confidence
    0.05
    skog
    0.05
    axed
    0.05
     quarters
    0.05
    Activations Density 0.008%

    No Known Activations