© 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. 20896
    Prev
    Next
    INDEX
    Explanations

    limited access or understanding

    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
    avan
    -0.07
    -generator
    -0.07
    оÑĢма
    -0.07
     limita
    -0.07
     limit
    -0.07
    产çļĦ
    -0.06
    iveau
    -0.06
    retta
    -0.06
    hood
    -0.06
    batas
    -0.06
    POSITIVE LOGITS
    s
    0.07
    Ñĸ
    0.06
    Âł
    0.05
    iskey
    0.05
     lyc
    0.05
    sen
    0.05
    人马
    0.05
    æĭ¢
    0.05
    found
    0.05
     lại
    0.05
    Activations Density 0.009%

    No Known Activations