© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19550
    Prev
    Next
    INDEX
    Explanations

    emphasis on

    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
     radicale
    -0.07
    iby
    -0.07
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.07
    Õ¡Õ¿
    -0.07
    examen
    -0.06
    мÑĸна
    -0.06
    eni
    -0.06
    é¤Ĭ
    -0.06
    ariat
    -0.06
    cies
    -0.06
    POSITIVE LOGITS
    该项
    0.06
     âĢ¦
    0.05
    N
    0.05
    0.04
    ä¿ı
    0.04
    (...)
    0.04
    è´Ńçī©
    0.04
    æīĵéĢļ
    0.04
    å§Ķä¼ļ
    0.04
    åĽŀäºĭ
    0.04
    Activations Density 0.005%

    No Known Activations