© 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. 18203
    Prev
    Next
    INDEX
    Explanations

    have/has/made/led/work/provide

    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
    åĬ¡
    -0.05
     (
    -0.05
    èݫ大çļĦ
    -0.05
    embros
    -0.05
    allow
    -0.05
    -this
    -0.05
    flate
    -0.05
    illar
    -0.05
    .
    -0.05
    oris
    -0.05
    POSITIVE LOGITS
    並以
    0.06
    ä¸ĢèĪ¬æľī
    0.06
     Tent
    0.06
     ë°©ë²ķìľ¼ë¡ľ
    0.06
    ekom
    0.06
    .utcnow
    0.06
     hoa
    0.06
    ä¸Ģå®ļä¸įä¼ļ
    0.06
    æĬĢæľ¯èµĦæĸĻ
    0.06
     bowiem
    0.06
    Activations Density 0.019%

    No Known Activations