© 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. 19996
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions/equations

    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
    ä½ĩ
    -0.07
    ấn
    -0.07
    odel
    -0.06
     curse
    -0.06
    allah
    -0.06
    æĹ¥æĹ©ä¸Ĭ
    -0.06
    èİ
    -0.06
     attempted
    -0.06
    ä¸Ģè¯ķ
    -0.06
    éĺµ
    -0.06
    POSITIVE LOGITS
    rp
    0.06
    å¢ŀæĶ¶
    0.05
     off
    0.05
    çŁĽçĽ¾
    0.05
    ãĢħ
    0.05
    没
    0.05
    docs
    0.05
    çĸijä¼¼
    0.05
     (
    0.04
    建议书
    0.04
    Activations Density 0.001%

    No Known Activations