© 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. 20441
    Prev
    Next
    INDEX
    Explanations

    stares back, handshake, catch eye

    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
    亿ä¸ĩ
    -0.06
    ảnh
    -0.06
    人æīĭ
    -0.06
    óf
    -0.06
    ermo
    -0.05
    æ²ĥæĸ¯
    -0.05
    Resta
    -0.05
    æĹ¥ä¸º
    -0.05
    rÃŃan
    -0.05
    èł
    -0.05
    POSITIVE LOGITS
    å®Ī
    0.06
     uncomfort
    0.05
    еÑĩе
    0.05
     socially
    0.05
    æĭī
    0.05
     stead
    0.05
    idd
    0.05
    åľ°
    0.05
    isses
    0.05
    stead
    0.05
    Activations Density 0.001%

    No Known Activations