© 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. 20488
    Prev
    Next
    INDEX
    Explanations

    U8glib, LiquidCrystal, display, module

    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
    -0.06
     differ
    -0.05
    åºķæĿ¿
    -0.05
    λεί
    -0.05
    çħ§
    -0.05
    çĸ¼
    -0.05
    åºŁ
    -0.05
    åºķ
    -0.05
     torn
    -0.05
    -files
    -0.05
    POSITIVE LOGITS
    olicit
    0.07
    驾
    0.07
    ä¸Ģè¾Ī
    0.06
    keit
    0.06
    iht
    0.06
    ukke
    0.06
    åĪ°èĩªå·±
    0.06
    jeti
    0.06
    ä¸Ģ空
    0.06
    oksi
    0.06
    Activations Density 0.001%

    No Known Activations