© 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. 18327
    Prev
    Next
    INDEX
    Explanations

    code structure tokens

    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
    ä¸įä¼ļåĽłä¸º
    -0.06
    åĵģ
    -0.06
    âĸª
    -0.05
    åŃĶæĺİ
    -0.05
     Fra
    -0.05
    _formats
    -0.05
    æ¦ľ
    -0.05
    综
    -0.05
    ener
    -0.05
    umbo
    -0.05
    POSITIVE LOGITS
    让èĩªå·±
    0.06
     subclass
    0.05
    ä¹ĭ交
    0.05
    ãĥįãĥ«
    0.05
    ä»¤ä½ł
    0.05
    äºĪ以
    0.05
    为ä¹ĭ
    0.05
    apsed
    0.05
     so
    0.05
    تÙĩا
    0.05
    Activations Density 0.021%

    No Known Activations