© 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. 18964
    Prev
    Next
    INDEX
    Explanations

    introduces, two, Chinese, stating, walked

    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
    åı¯ä»¥åĪ©çĶ¨
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    воÑĢо
    -0.05
    åı¯åĪ©çĶ¨
    -0.05
    ç²
    -0.05
    evel
    -0.05
    æĸĽ
    -0.05
    æļĩ
    -0.05
    ÑĩаÑı
    -0.05
    æľīæīĢ
    -0.05
    POSITIVE LOGITS
    ä¹ĭä¸ī
    0.06
    é¼İ
    0.06
    mys
    0.06
     Alleg
    0.06
     excuse
    0.06
    éĸ£
    0.05
    subst
    0.05
    aur
    0.05
    erts
    0.05
    åħ¶ä¸ī
    0.05
    Activations Density 0.001%

    No Known Activations