© 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. 21871
    Prev
    Next
    INDEX
    Explanations

    output to console

    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
    æĪĸåľ¨
    -0.05
    gur
    -0.05
    gabe
    -0.05
    atii
    -0.05
    atih
    -0.05
    ibat
    -0.05
    庵
    -0.05
    empl
    -0.05
     ÑįкÑģпеÑĢÑĤи
    -0.05
    onaut
    -0.05
    POSITIVE LOGITS
    ä¸Ģ缮
    0.07
    ä¸ĢæľĽ
    0.06
    çĬ¶åħĥ
    0.06
    [o
    0.06
    mons
    0.06
    æľī天
    0.06
     suon
    0.06
    (pol
    0.06
    çݩ家们
    0.06
    æĿ¥å¾Ĺ
    0.06
    Activations Density 0.003%

    No Known Activations