© 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. 18443
    Prev
    Next
    INDEX
    Explanations

    normally, notoriously

    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
     pockets
    -0.05
    å¼Ģ好
    -0.05
    åı£å¾Ħ
    -0.05
    æĺ¯åľ¨
    -0.05
    ÑĤки
    -0.05
    类似çļĦ
    -0.05
    缸åħ³çļĦ
    -0.05
    åıĮåĢį
    -0.04
    ermann
    -0.04
    Ñĩ
    -0.04
    POSITIVE LOGITS
     normally
    0.08
     Normally
    0.07
    normally
    0.07
     usual
    0.06
     notoriously
    0.06
    åIJijæĿ¥
    0.06
    WISE
    0.06
    atern
    0.06
    ãģĵãģ¨ãģªãģı
    0.06
     notorious
    0.06
    Activations Density 0.128%

    No Known Activations