© 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. 18651
    Prev
    Next
    INDEX
    Explanations

    html tags and css classes

    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
    è¿Ľè¡ĮæIJľç´¢
    -0.06
    гÑĢе
    -0.06
    并åıĸå¾Ĺ
    -0.06
    西å¸Ĥ
    -0.06
    cratch
    -0.06
    {return
    -0.06
    ä¸įä½ı
    -0.06
    atas
    -0.05
    åĸ§åĵĹ
    -0.05
    è¦ģ说
    -0.05
    POSITIVE LOGITS
    Ŀ
    0.06
    iar
    0.06
    èĮ¨
    0.05
    å¸Ī
    0.05
    icha
    0.05
    ologio
    0.05
    ajem
    0.05
    reiben
    0.05
    ected
    0.05
    ismo
    0.05
    Activations Density 0.033%

    No Known Activations