© 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. 37856
    Prev
    Next
    INDEX
    Explanations

    bursting, detonation, button, bifur, shootout

    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
     occasional
    -0.06
    åijĬ
    -0.06
    leit
    -0.06
    inder
    -0.06
    -0.06
    æł¹æį®ä¸įåIJĮçļĦ
    -0.06
    RI
    -0.06
     bed
    -0.06
    engang
    -0.05
    è¿Ŀåıį
    -0.05
    POSITIVE LOGITS
    缴æİ¥åľ¨
    0.15
    _inside
    0.13
    è®¾åľ¨
    0.12
    åıijçĶŁåľ¨
    0.12
     innerhalb
    0.12
     داخÙĦ
    0.12
    à¹ĥà¸Ļà¸ŀืà¹īà¸Ļà¸Ĺีà¹Ī
    0.11
    设äºİ
    0.11
     inside
    0.11
    Inside
    0.11
    Activations Density 0.310%

    No Known Activations