© 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. 18662
    Prev
    Next
    INDEX
    Explanations

    code file paths

    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
    deÅŁ
    -0.06
    å¥ī
    -0.06
    ãģ¤ãĤĤãĤĬ
    -0.05
     Whats
    -0.05
    paque
    -0.05
    θεια
    -0.05
     conseg
    -0.05
     cắn
    -0.05
    æĦıæĮĩ
    -0.05
    nahm
    -0.05
    POSITIVE LOGITS
    æĽĿ
    0.07
    ä¸ĭåIJĮ
    0.05
    insel
    0.05
    olis
    0.05
     spec
    0.05
    levator
    0.05
    çĸij
    0.05
     (
    0.05
    oso
    0.05
    aras
    0.05
    Activations Density 0.151%

    No Known Activations