© 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. 18326
    Prev
    Next
    INDEX
    Explanations

    new server infrastructure

    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
    ä¸įåIJĮçļĦ人
    -0.05
    elib
    -0.05
    è¾ĵ
    -0.05
    ye
    -0.05
     different
    -0.05
     Barber
    -0.05
    çĶ³è¯·è¡¨
    -0.05
    different
    -0.05
    æıĴ
    -0.05
     extrapol
    -0.05
    POSITIVE LOGITS
    è¶ĬæĿ¥è¶Ĭå¤ļçļĦ
    0.07
    éĢIJæŃ¥
    0.07
    æİ¥çıŃ
    0.07
     gradually
    0.07
    åıĸ代
    0.07
     تدرÙĬ
    0.07
    æĽ¿ä»£åĵģ
    0.07
    ubern
    0.06
    éĢIJæ¸IJæĪIJ为
    0.06
    ãģĦãģ¤
    0.06
    Activations Density 0.062%

    No Known Activations