© 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. 19999
    Prev
    Next
    INDEX
    Explanations

    numbers relating to time or quantity

    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
    ouden
    -0.07
    å¤ļ级
    -0.06
     leveled
    -0.06
    hill
    -0.06
    arter
    -0.06
    arangan
    -0.06
    -Sah
    -0.06
    ัส
    -0.06
    æľīåĬ©
    -0.06
    _lvl
    -0.06
    POSITIVE LOGITS
    forge
    0.06
    ç§ī
    0.06
    缴æİ¥æĪĸ
    0.05
     present
    0.05
    并ç»ı
    0.05
    irian
    0.05
     mass
    0.05
    æ³¼
    0.05
    ï¼Ī
    0.05
     Rowe
    0.05
    Activations Density 0.001%

    No Known Activations