© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22540
    Prev
    Next
    INDEX
    Explanations

    first person or only one

    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
    Negative Logits
    ól
    -0.06
    大ä¼ļ
    -0.05
    MouseButton
    -0.05
    andan
    -0.05
    æľª
    -0.05
    aille
    -0.05
    panied
    -0.05
    zun
    -0.05
    Convention
    -0.05
    ä¼łè¾¾äºĨ
    -0.05
    POSITIVE LOGITS
    orget
    0.05
    åĽºå®ļçļĦ
    0.05
    inspace
    0.05
    ä»Ĭå¹´ä¸ĬåįĬå¹´
    0.05
     Nova
    0.05
     configur
    0.05
    yron
    0.05
    Occup
    0.05
    åĵ¥çļĦ
    0.05
    èĢĮéĿŀ
    0.05
    Activations Density 0.043%

    No Known Activations