© 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. 20052
    Prev
    Next
    INDEX
    Explanations

    cleaning and hygiene actions

    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
    command
    -0.06
    erein
    -0.06
     magic
    -0.06
    è¾
    -0.05
    io
    -0.05
    seau
    -0.05
    vious
    -0.05
    stitial
    -0.05
    -ground
    -0.05
    stderr
    -0.05
    POSITIVE LOGITS
    æįı
    0.06
    éĿ¢éĿ¢
    0.05
     алÑĮ
    0.05
    Transient
    0.05
    æł¸ç®Ĺ
    0.05
     Pras
    0.05
    ilis
    0.05
    otis
    0.05
    struk
    0.05
    surf
    0.05
    Activations Density 0.003%

    No Known Activations