© 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. 21938
    Prev
    Next
    INDEX
    Explanations

    return their items

    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
    aku
    -0.06
    ä¸įæĶ¾
    -0.06
    äºĪ以
    -0.06
    urier
    -0.06
     tutup
    -0.05
    zan
    -0.05
     splitted
    -0.05
    alleries
    -0.05
    éķ¿åħ´
    -0.05
     اÙĦØ¥ÙĨ
    -0.05
    POSITIVE LOGITS
    åĶ
    0.06
    æľªç»ı
    0.05
    åª
    0.05
    à¸ŀ
    0.05
    ügen
    0.05
    squ
    0.05
    æľª
    0.05
    ä¸įæĺ¯å¾Ī
    0.05
    formance
    0.05
    sq
    0.05
    Activations Density 0.001%

    No Known Activations