© 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. 11406
    Prev
    Next
    INDEX
    Explanations

    value, result, settlement

    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
    沿
    -0.08
     <",
    -0.08
    ppi
    -0.08
    ordi
    -0.08
    è´¹çĶ¨çĶ±
    -0.07
    ìŀ¡
    -0.07
    ajer
    -0.07
    类似çļĦ
    -0.07
    _TEMPLATE
    -0.07
    åıĪä¸Ģ
    -0.07
    POSITIVE LOGITS
    æŃ£ç¡®çŃĶæ¡Ī
    0.08
    çŃĶæ¡Īæĺ¯
    0.08
    çļĦçŃĶæ¡Ī
    0.08
     vind
    0.08
     correct
    0.08
     correctness
    0.08
    åĩĨç¡®çļĦ
    0.07
    çļĦæŃ£ç¡®
    0.07
    æŃ£ç¡®çļĦ
    0.07
     substant
    0.07
    Activations Density 0.007%

    No Known Activations