© 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. 17859
    Prev
    Next
    INDEX
    Explanations

    in a place

    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
    æĦŁåįģ足
    -0.06
    ä¼ģä¸ļä¸İ
    -0.06
    arı
    -0.05
    å±ĢåĬ¿
    -0.05
    æ°ĶåĬ¿
    -0.05
    å®ı大
    -0.05
     kesel
    -0.05
    etik
    -0.05
    /import
    -0.05
    etics
    -0.05
    POSITIVE LOGITS
    -repeat
    0.06
    jada
    0.06
    bout
    0.06
    è½®çļĦ
    0.06
    {$
    0.05
    ellini
    0.05
     repeat
    0.05
    åĽī
    0.05
    repeat
    0.05
    mato
    0.05
    Activations Density 0.086%

    No Known Activations