© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17798
    Prev
    Next
    INDEX
    Explanations

    local repo

    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
    grad
    -0.06
    vore
    -0.06
    artet
    -0.06
    alisierte
    -0.06
    å¾Īç¾İ
    -0.06
    efa
    -0.06
    uae
    -0.06
    é¢ľ
    -0.06
    onan
    -0.06
     EF
    -0.05
    POSITIVE LOGITS
    ضÙħ
    0.06
    æŃ¢
    0.06
    串
    0.05
    æıIJåīį
    0.05
    à¹īา
    0.05
    ÏĦÏģο
    0.05
    ä¸Ĭä¸Ģ个
    0.05
     divul
    0.05
    icias
    0.05
    符
    0.05
    Activations Density 0.024%

    No Known Activations