© 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. 17032
    Prev
    Next
    INDEX
    Explanations

    special characters, placeholders, symbols, NULL

    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
    ivet
    -0.06
    erais
    -0.06
    umann
    -0.05
    IAS
    -0.05
    zÃŃ
    -0.05
    azel
    -0.05
    apl
    -0.05
    emel
    -0.05
    ä¼łä¸ĸ
    -0.05
    portun
    -0.05
    POSITIVE LOGITS
    æľīä½Ļ
    0.06
    æĬ½è±¡
    0.06
    èĥ½åĬĽå¼º
    0.06
    å¿łå®ŀ
    0.06
    блей
    0.06
    concept
    0.05
    çŃĭ
    0.05
    æŨ
    0.05
    UNK
    0.05
    éħ·
    0.05
    Activations Density 0.013%

    No Known Activations