© 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. 21247
    Prev
    Next
    INDEX
    Explanations

    references and licenses

    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
    ancel
    -0.05
    é»ĺ
    -0.05
    éĥ¨å§Ķ
    -0.05
    ضة
    -0.05
     simul
    -0.05
    ừng
    -0.05
    faz
    -0.05
    veni
    -0.05
    erten
    -0.05
    å·¥ä½ľä¸ŃçļĦ
    -0.05
    POSITIVE LOGITS
    ot
    0.06
    otropic
    0.06
    à´£àµį
    0.06
    ius
    0.06
    åºķ
    0.06
    ä»»ä½ķåħ¶ä»ĸ
    0.05
    ä¸ĭåIJĮ
    0.05
     bÃłng
    0.05
    åĿĩ
    0.05
    NG
    0.05
    Activations Density 0.001%

    No Known Activations