© 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. 18914
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    uil
    -0.06
    æĪ¸
    -0.06
    ifferential
    -0.06
    è··
    -0.06
    ech
    -0.06
    èĭ±æĸĩåIJįåŃĹ
    -0.06
    ank
    -0.06
    gebühr
    -0.05
    amp
    -0.05
    èĭ¥æĹł
    -0.05
    POSITIVE LOGITS
    estring
    0.05
    æĦıåĽ¾
    0.05
    uten
    0.05
    åį¿
    0.05
    OrFail
    0.05
    sent
    0.05
    poser
    0.05
    razia
    0.05
    ÑİÑĢ
    0.05
    XHR
    0.05
    Activations Density 0.001%

    No Known Activations