© 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. 50319
    Prev
    Next
    INDEX
    Explanations

    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
     distanci
    -0.08
     amidst
    -0.07
    Clone
    -0.07
     lá»ĵng
    -0.07
    rast
    -0.07
    shade
    -0.07
    éģįåıĬ
    -0.07
     distances
    -0.07
    ึà¹Īà¸ĩ
    -0.07
    询价
    -0.07
    POSITIVE LOGITS
     boundary
    0.15
    è¾¹çķĮ
    0.14
    åħ¥åı£å¤Ħ
    0.13
    éŨåı£
    0.13
    æİ¥åı£
    0.13
     terminal
    0.13
    è¾¹ç¼ĺ
    0.13
    boundary
    0.13
     endpoint
    0.13
     borderTop
    0.12
    Activations Density 0.612%

    No Known Activations