© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19469
    Prev
    Next
    INDEX
    Explanations

    finding vehicles in texts

    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
    idal
    -0.07
    raje
    -0.06
    åıĭæĥħ
    -0.06
    ç¡®ä¿Ŀå®īåħ¨
    -0.06
    petto
    -0.06
     ลà¹īาà¸Ļà¸Ķà¸Ńลลารà¹Į
    -0.06
    ä¹Łä¸įçŁ¥éģĵ
    -0.06
    ós
    -0.05
    leun
    -0.05
    -os
    -0.05
    POSITIVE LOGITS
    æ¦Ĥ
    0.05
    è·Łè¸ª
    0.05
    å¾®
    0.05
    åįĥåįĥ
    0.05
    åŁºç¡Ģ
    0.05
    lw
    0.05
     implicated
    0.05
    trail
    0.05
    è·Łè¿Ľ
    0.05
    olan
    0.05
    Activations Density 0.011%

    No Known Activations