© 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. 20827
    Prev
    Next
    INDEX
    Explanations

    value range or boundary

    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
    ums
    -0.06
    oden
    -0.06
     partition
    -0.06
    Ñıн
    -0.05
    解æĶ¾
    -0.05
     اÙĦعاÙħÙĦØ©
    -0.05
    olf
    -0.05
    olum
    -0.05
     Partition
    -0.05
    partition
    -0.05
    POSITIVE LOGITS
     fav
    0.05
    ä¼¸çĽ´
    0.05
    ä¸įå¼ĥ
    0.05
    常åĬ¡
    0.05
    ZY
    0.05
    chal
    0.05
    ä¸įéĹ®
    0.05
     sidelines
    0.05
     unanswered
    0.05
    åľ°è´¨
    0.05
    Activations Density 0.013%

    No Known Activations