© 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. 20637
    Prev
    Next
    INDEX
    Explanations

    computer hardware components

    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
    zo
    -0.06
    ç¬ĶèĢħ认为
    -0.05
     relief
    -0.05
    ä¸įæīĵ
    -0.05
    缴è§ĤçļĦæĸ¹å¼ı
    -0.05
    .apple
    -0.05
    åĪ°åºķ
    -0.05
     traditionally
    -0.05
     Relief
    -0.05
    夫
    -0.05
    POSITIVE LOGITS
    reste
    0.06
    ác
    0.06
    ernet
    0.06
    egrated
    0.06
    ä¸ĩåįĥ
    0.05
    ÅĽciÄħ
    0.05
    áter
    0.05
    ellit
    0.05
    ä¸Ĭåı£
    0.05
    iples
    0.05
    Activations Density 0.003%

    No Known Activations