© 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. 21336
    Prev
    Next
    INDEX
    Explanations

    context or background

    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
    deen
    -0.07
    untas
    -0.07
     ÑģобÑĢ
    -0.06
     sedu
    -0.06
    ç«ŀäºīé£İéĻ©
    -0.06
    ders
    -0.06
    iegel
    -0.06
    cripcion
    -0.06
    SqlCommand
    -0.06
    uctions
    -0.06
    POSITIVE LOGITS
    åı¯ä»¥çIJĨ解
    0.06
    appr
    0.05
     real
    0.05
    illa
    0.05
    G
    0.05
     G
    0.05
    åŁº
    0.05
    ä¸ĩæĸ¹
    0.05
    è´°
    0.05
     private
    0.05
    Activations Density 0.040%

    No Known Activations