© 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. 17528
    Prev
    Next
    INDEX
    Explanations

    happened quickly / without warning

    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
    onda
    -0.06
    alled
    -0.06
    asse
    -0.06
    wijk
    -0.06
    èļĵ
    -0.06
    ako
    -0.06
    omy
    -0.06
    åģıåģı
    -0.05
    biet
    -0.05
    amat
    -0.05
    POSITIVE LOGITS
    è¿ĩç¨ĭ
    0.06
    ä¸įçŁ¥ä¸įè§ī
    0.06
    æĻ¨
    0.06
    æħİ
    0.06
    -init
    0.05
    æĸ¹ä¾¿
    0.05
    iture
    0.05
    C
    0.05
    è·Łè¿Ľ
    0.05
     plur
    0.05
    Activations Density 0.017%

    No Known Activations