© 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. 20005
    Prev
    Next
    INDEX
    Explanations

    404 errors

    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
    Fore
    -0.06
    åģ¥
    -0.06
    ä¿Ĭ
    -0.06
    re
    -0.06
     arrestato
    -0.05
    éªı
    -0.05
    unds
    -0.05
    wor
    -0.05
    æĬ¤
    -0.05
    ivin
    -0.05
    POSITIVE LOGITS
    edy
    0.06
    gary
    0.06
    edom
    0.06
    adah
    0.06
    SAME
    0.05
    yro
    0.05
    kah
    0.05
    alaman
    0.05
    表示äºĨ
    0.05
    æĮĤäºĨ
    0.05
    Activations Density 0.017%

    No Known Activations