© 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. 18193
    Prev
    Next
    INDEX
    Explanations

    meaning

    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
    otten
    -0.06
    åı¤ä»£
    -0.06
     Akron
    -0.05
    é
    -0.05
    atters
    -0.05
    çļĦåĽłç´ł
    -0.05
    æĽ´éĩįè¦ģçļĦ
    -0.05
     crucial
    -0.05
    à¸ģุ
    -0.05
     undone
    -0.05
    POSITIVE LOGITS
    ifel
    0.08
    èĭ±æĸĩåIJįåŃĹ
    0.06
    plib
    0.06
    plom
    0.06
    çĦ¡éĻIJ
    0.06
    patr
    0.06
    rones
    0.06
     канд
    0.06
     تعÙĦ
    0.06
    ç½®åľ°
    0.06
    Activations Density 0.006%

    No Known Activations