© 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. 17330
    Prev
    Next
    INDEX
    Explanations

    log files and status

    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
    缮
    -0.06
    aille
    -0.05
    Ģ
    -0.05
    ack
    -0.05
    anzi
    -0.05
    dot
    -0.05
    äst
    -0.05
    igram
    -0.05
    ç´¢æĢ§
    -0.05
    à¹Ģหà¹ĩà¸Ļ
    -0.05
    POSITIVE LOGITS
    rières
    0.07
    IPS
    0.07
    ÙħÙĨÙĬ
    0.07
    ANGED
    0.07
    è¿ĻäºĽåľ°æĸ¹
    0.06
     pär
    0.06
    มà¸Ļ
    0.06
    æĭĽçĶŁèĢĥè¯ķ
    0.06
    åĬłå·¥å·¥èīº
    0.06
    à¹Ģลà¸Ļ
    0.06
    Activations Density 0.014%

    No Known Activations