© 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. 7536
    Prev
    Next
    INDEX
    Explanations

    mediciones of

    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
    åĬłæĭ¿å¤§
    -0.07
     Indah
    -0.06
    lessness
    -0.06
    eso
    -0.06
    å¿«åĪ°
    -0.06
    оÑĢе
    -0.06
    ensitivity
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    uo
    -0.06
    endale
    -0.06
    POSITIVE LOGITS
    ฯ
    0.09
    èĩªå·±çļĦ缮æłĩ
    0.07
    ông
    0.07
    onna
    0.07
    .community
    0.06
    缴æİ¥æĪĸ
    0.06
    èĵī
    0.06
    å¿ĥæĢĢ
    0.06
     cellspacing
    0.06
    Ĺı
    0.06
    Activations Density 0.264%

    No Known Activations