© 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. 22040
    Prev
    Next
    INDEX
    Explanations

    below is an example

    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
    wendungen
    -0.07
    onis
    -0.07
     zove
    -0.06
    群ä¼ĹåĬŀå®ŀäºĭ
    -0.06
    rano
    -0.06
    undi
    -0.06
    wine
    -0.06
     ÙħÙĪجب
    -0.06
    åĸ½
    -0.06
    inda
    -0.06
    POSITIVE LOGITS
    å·±
    0.05
    ä¸Ģå¼Ģå§ĭ
    0.05
    le
    0.05
    示ä¾ĭ
    0.05
     exemplary
    0.05
    Nil
    0.05
    èĽĩ
    0.05
     example
    0.05
    以å¾Ģ
    0.05
     explicit
    0.05
    Activations Density 0.071%

    No Known Activations