© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19460
    Prev
    Next
    INDEX
    Explanations

    CREATE TABLE AUTOINCREMENT

    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
    æݧèĤ¡éĽĨåĽ¢æľīéĻIJåħ¬åı¸
    -0.07
    iegel
    -0.07
    ilhas
    -0.06
    izzo
    -0.06
    lund
    -0.06
    éĤ£åı¯æĺ¯
    -0.06
    endoza
    -0.06
    noz
    -0.06
    мÑĭÑĪ
    -0.06
     terce
    -0.06
    POSITIVE LOGITS
     experiment
    0.05
    é¢ĺ
    0.05
     gre
    0.05
     real
    0.05
    ctime
    0.05
    èĭŁ
    0.05
    å®ŀéªĮ
    0.04
    ìĭ¤
    0.04
     pró
    0.04
     g
    0.04
    Activations Density 0.003%

    No Known Activations