© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10706
    Prev
    Next
    INDEX
    Explanations

    tournament stages

    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
    æī¹éĩı
    -0.07
    ä¸ĭ课
    -0.07
    å¾®
    -0.06
    anga
    -0.06
    ole
    -0.06
    æ·ĩ
    -0.06
    oyal
    -0.06
    gaz
    -0.06
     Spar
    -0.06
    Shift
    -0.06
    POSITIVE LOGITS
    èµĦæł¼å®¡æŁ¥
    0.10
    æ·ĺæ±°
    0.10
    -stage
    0.09
     stages
    0.09
    缴éĢļ
    0.09
    æĬ½çŃ¾
    0.09
     elimin
    0.09
    çŃĽéĢī
    0.09
     elim
    0.09
     stage
    0.09
    Activations Density 0.241%

    No Known Activations