© 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. 21684
    Prev
    Next
    INDEX
    Explanations

    lyrics, seasons, movies

    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
    agara
    -0.05
    great
    -0.05
     blend
    -0.05
    ä¹Ķ
    -0.05
     kand
    -0.05
    elin
    -0.05
    æĸĩæijĺ
    -0.05
    ë¡ľ
    -0.05
    .db
    -0.05
    éģĵ
    -0.05
    POSITIVE LOGITS
     %-
    0.06
    æĢ§æĺ¯
    0.06
    åĺĢåĴķ
    0.06
     suspicious
    0.05
    uchen
    0.05
    etlen
    0.05
    æľīèĩ´
    0.05
    utile
    0.05
    åħ¬åı¸ä¸º
    0.05
    æĺ¯ä¸Ģ个人
    0.05
    Activations Density 0.001%

    No Known Activations