© 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. 21327
    Prev
    Next
    INDEX
    Explanations

    formally announce

    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
    hone
    -0.07
    isco
    -0.06
    apak
    -0.06
    otent
    -0.06
    æħķ
    -0.06
    gelt
    -0.06
    oger
    -0.05
    主åĬ¨åIJij
    -0.05
    ader
    -0.05
    ogra
    -0.05
    POSITIVE LOGITS
    ستاÙĨ
    0.06
    éļıåľ°
    0.05
     singled
    0.05
    æĸ¹éĿ¢
    0.05
    embers
    0.05
    æ¯Ķæ¯Ķ
    0.05
    ash
    0.05
    å¦ĤæѤ
    0.05
    lor
    0.05
    ÏĦια
    0.05
    Activations Density 0.001%

    No Known Activations