© 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. 17115
    Prev
    Next
    INDEX
    Explanations

    abbreviations ending in TS, CAT, HT, ST, RN, FT

    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
    ÑģÑĤеÑģÑĤвенно
    -0.07
    ä½Ļ人次
    -0.06
    çļĦåİŁåĽłä¹ĭä¸Ģ
    -0.06
    lut
    -0.06
    usse
    -0.06
    åľ°åİ»
    -0.06
    ä½Ļ亩
    -0.06
    roys
    -0.06
    urge
    -0.06
     voile
    -0.06
    POSITIVE LOGITS
    ation
    0.06
    orada
    0.05
     Bon
    0.05
    amakan
    0.05
     once
    0.05
    ewn
    0.04
    èĤ¢
    0.04
    ساب
    0.04
    ?
    0.04
    witz
    0.04
    Activations Density 0.143%

    No Known Activations