© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20125
    Prev
    Next
    INDEX
    Explanations

    colors and materials

    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
    ast
    -0.05
    èµ·
    -0.05
    upro
    -0.05
    ä»ij
    -0.05
    代
    -0.05
    æĮĩæķ°
    -0.05
     Moro
    -0.05
     als
    -0.05
    åıijçĶŁåľ¨
    -0.05
    æİĪæĿĥ
    -0.05
    POSITIVE LOGITS
    lež
    0.07
    ogne
    0.07
    NESS
    0.07
    WISE
    0.07
     próxim
    0.06
    çļĦè¿ij
    0.06
    thetic
    0.06
    -With
    0.06
    çļĦé«ĺ级
    0.06
    è¿Ļé¡¹å·¥ä½ľ
    0.06
    Activations Density 0.018%

    No Known Activations