© 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. 42170
    Prev
    Next
    INDEX
    Explanations

    turns and corners

    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
    undur
    -0.08
    榻
    -0.07
    awah
    -0.07
    æĹ¥ä¸Ĭ
    -0.07
    çĪ¬åĪ°
    -0.07
     sno
    -0.07
    æµ®
    -0.06
     Kund
    -0.06
    åĤ¬
    -0.06
    åĪ°æīĭ
    -0.06
    POSITIVE LOGITS
    转弯
    0.12
    转
    0.10
    ä¸Ģ转
    0.10
    弯éģĵ
    0.10
    弧
    0.10
    åı³è½¬
    0.10
    弯路
    0.09
    转åĩº
    0.09
     bend
    0.09
    .turn
    0.09
    Activations Density 0.033%

    No Known Activations