© 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. 18278
    Prev
    Next
    INDEX
    Explanations

    clear advantage

    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
    ä½łæĶ¾å¿ĥ
    -0.06
    лиÑĤÑĮÑģÑı
    -0.06
    nement
    -0.06
    resher
    -0.05
    oodle
    -0.05
     fixing
    -0.05
    设æĸ½
    -0.05
    ices
    -0.05
    plex
    -0.05
    éĻħ
    -0.05
    POSITIVE LOGITS
    ónimo
    0.06
    inach
    0.06
    ÑħÑĸд
    0.06
    æľīæĿ¡ä»¶çļĦ
    0.06
    æľīæĿ¡ä»¶
    0.06
     khép
    0.05
    trait
    0.05
    athed
    0.05
    udo
    0.05
    Ñģлед
    0.05
    Activations Density 0.002%

    No Known Activations