© 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. 19919
    Prev
    Next
    INDEX
    Explanations

    sleek sophistication

    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
    è¿ĩ渡
    -0.06
     transitional
    -0.05
     transition
    -0.05
    åı°å¤§
    -0.05
    arton
    -0.05
    æģ°
    -0.05
    orgia
    -0.05
    Ùĩار
    -0.05
    hr
    -0.05
    transition
    -0.05
    POSITIVE LOGITS
     sleek
    0.08
    æµģ线
    0.07
     Sle
    0.07
     ÄijÃŃch
    0.06
    eleg
    0.06
    zub
    0.06
     ÑĨелÑĮÑİ
    0.06
    æį®æĬ¥éģĵ
    0.06
    andest
    0.06
    amping
    0.06
    Activations Density 0.002%

    No Known Activations