© 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. 55722
    Prev
    Next
    INDEX
    Explanations

    north, side, border

    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
    سع
    -0.07
    åģ¶çĦ¶
    -0.07
    ellis
    -0.07
    åĿĩè¡¡
    -0.06
    rego
    -0.06
    åĮ¹éħį
    -0.06
    åĮ¹éħįçļĦ
    -0.06
     koc
    -0.06
    ãĥĥãĤ·ãĥ¥
    -0.06
    apt
    -0.06
    POSITIVE LOGITS
    ç»ķè¡Į
    0.08
    缴æİ¥è¿Ľåħ¥
    0.08
    zi
    0.08
    ×Ļ׳×ķ
    0.08
    ëĿ¼ìĿ¸
    0.07
    注åĨĮèµĦæľ¬ä¸º
    0.07
     Entre
    0.07
    åĪ·åĪ·
    0.07
    çŃĭ
    0.07
    ç»ķè¿ĩ
    0.07
    Activations Density 0.001%

    No Known Activations