© 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. 18924
    Prev
    Next
    INDEX
    Explanations

    quantities or limits

    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
    ux
    -0.07
    uz
    -0.06
    ä¸įæĶ¾
    -0.06
    ìĻĦ
    -0.05
    zust
    -0.05
    butt
    -0.05
     "{
    -0.05
     punteggio
    -0.05
    ä¸į移
    -0.05
    åħģ
    -0.05
    POSITIVE LOGITS
    imir
    0.07
    imers
    0.06
    æīĵçł´
    0.05
    rake
    0.05
     indent
    0.05
    åįģä¹Ŀ大
    0.05
     ingle
    0.05
     conveniently
    0.05
    ëĭĺ
    0.05
    ç©¿è¿ĩ
    0.05
    Activations Density 0.001%

    No Known Activations