© 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. 21232
    Prev
    Next
    INDEX
    Explanations

    studies citations

    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
     liv
    -0.06
    åĩºå¢ĥ
    -0.06
    enes
    -0.06
    llib
    -0.06
    udiant
    -0.06
    ĴĪ
    -0.06
    isel
    -0.06
    人æ°ijæĶ¿åºľ
    -0.06
    æİĪ
    -0.06
    andel
    -0.06
    POSITIVE LOGITS
    ä½Ļåħī
    0.06
    åij¨ä¸Ģ
    0.06
    awe
    0.05
    áŀ·
    0.05
    åĬ³
    0.05
    gle
    0.05
    arcy
    0.05
    æĭĿ
    0.05
    .guard
    0.05
    缸çľĭ
    0.05
    Activations Density 0.042%

    No Known Activations