© 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. 18575
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables and differentiation

    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
    GY
    -0.07
    ZY
    -0.07
    lese
    -0.06
     Saud
    -0.06
    ierno
    -0.06
     khay
    -0.06
    æīĢ欲
    -0.06
    archie
    -0.06
    еÑĢбÑĥ
    -0.06
    .Inf
    -0.06
    POSITIVE LOGITS
    mond
    0.05
    æ¯ıæĻļ
    0.05
    URN
    0.05
    ós
    0.05
    å¿ĺ
    0.05
    å¸ĥæŀĹ
    0.05
    è¾¼
    0.05
    æĪIJéķ¿ä¸º
    0.05
     Hayward
    0.05
     Centrum
    0.05
    Activations Density 0.023%

    No Known Activations