© 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. 17529
    Prev
    Next
    INDEX
    Explanations

    lounging, interrogating, irradiating, inoculating, clocked, mobilized, petitioned, carregando

    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
    edly
    -0.07
    ingg
    -0.06
    éģ©
    -0.06
    ждÑĥÑİ
    -0.06
    chst
    -0.06
    spre
    -0.06
    ÑģÑı
    -0.06
    olem
    -0.06
    èĨı
    -0.06
    ÑĤеле
    -0.06
    POSITIVE LOGITS
    watch
    0.05
    帮åĬ©å¤§å®¶
    0.05
    åħ±åIJĮä½ĵ
    0.05
    ueb
    0.04
    ç¶Ń
    0.04
    å´Ľ
    0.04
    owi
    0.04
    -wh
    0.04
    æĺ¯ä»Ģä¹Īæł·
    0.04
     puro
    0.04
    Activations Density 0.070%

    No Known Activations