© 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. 20392
    Prev
    Next
    INDEX
    Explanations

    bench press

    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
     wrapper
    -0.06
     concat
    -0.05
    -wrap
    -0.05
    çļĦä¸Ģç±»
    -0.05
    .wrapper
    -0.05
    æĨij
    -0.05
    è®°äºĭ
    -0.05
    æ»ĭ
    -0.05
    æŃ£ç¡®çļĦæĺ¯
    -0.05
     unt
    -0.05
    POSITIVE LOGITS
    åĿ¦
    0.09
    abb
    0.07
    aiser
    0.06
    uzzi
    0.06
    Touches
    0.06
     somewhere
    0.06
    imits
    0.05
     ÑģÑħод
    0.05
    urat
    0.05
    ukaan
    0.05
    Activations Density 0.003%

    No Known Activations