© 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. 19861
    Prev
    Next
    INDEX
    Explanations

    deprecated

    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
     Bai
    -0.05
    ä½ķ
    -0.05
    Ø°ÙĬ
    -0.05
     trailing
    -0.05
    ç¾ģæĬ¼
    -0.05
     оÑĤобÑĢа
    -0.05
     without
    -0.04
    ysz
    -0.04
     reg
    -0.04
    æ±ł
    -0.04
    POSITIVE LOGITS
    æĶ¹çĶ¨
    0.08
    otch
    0.07
     alternatives
    0.07
     alternative
    0.07
    alternative
    0.07
     Alternative
    0.07
    Alternative
    0.07
    ä¸įå½Ĵ
    0.07
    æĽ¿ä»£
    0.07
    Altern
    0.07
    Activations Density 0.298%

    No Known Activations