© 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. 21752
    Prev
    Next
    INDEX
    Explanations

    menu of

    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
    è±IJ
    -0.06
    omen
    -0.06
    abby
    -0.06
    éħ¸
    -0.05
    ÑĢÑģкого
    -0.05
    esia
    -0.05
     surve
    -0.05
    oire
    -0.05
    elui
    -0.05
    eron
    -0.05
    POSITIVE LOGITS
    ä¼ļåĦ¿
    0.06
    ulai
    0.06
    opy
    0.06
    ئÛĮ
    0.05
    ¥
    0.05
    æģº
    0.05
     casts
    0.05
    -Key
    0.05
    ajas
    0.05
    åŁİåįĹ
    0.05
    Activations Density 0.001%

    No Known Activations