© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27745
    Prev
    Next
    INDEX
    Explanations

    today, alley, old

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪ°æľī
    -0.08
    è¿Ļè¯Ŀ
    -0.08
     downlo
    -0.08
    IMER
    -0.08
    èIJ¥éĢł
    -0.08
    æĥħæĦ¿
    -0.08
    ffects
    -0.08
    êng
    -0.07
    å¾Ĺåĥı
    -0.07
    resco
    -0.07
    POSITIVE LOGITS
    æķħæѤ
    0.08
    èĢĮä¸Ķ
    0.07
    åĽłæѤ
    0.07
     bur
    0.07
     Moreover
    0.07
    Moreover
    0.07
    èĢĮä¸Ķåľ¨
    0.07
    om
    0.07
     Therefore
    0.07
    åıªä¸įè¿ĩ
    0.07
    Activations Density 0.044%

    No Known Activations