© 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. 19852
    Prev
    Next
    INDEX
    Explanations

    programming include statements

    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
    Ĭ
    -0.06
    æĹłå½¢
    -0.06
    è¶ħ大
    -0.06
    .TryParse
    -0.06
    .OrderByDescending
    -0.06
    -0.05
     bounding
    -0.05
    emain
    -0.05
     ÑģпÑĢавки
    -0.05
    licative
    -0.05
    POSITIVE LOGITS
    çµ²
    0.06
    lek
    0.06
    ä¸Ŀ
    0.06
    naf
    0.05
    nali
    0.05
    zyman
    0.05
    ég
    0.05
    makers
    0.05
     revenir
    0.05
    ams
    0.05
    Activations Density 0.001%

    No Known Activations