© 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. 30383
    Prev
    Next
    INDEX
    Explanations

    edges and boundaries

    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
     Einst
    -0.07
    åħ¨åĽ½ç»Łä¸Ģ
    -0.07
    anguard
    -0.07
     Worlds
    -0.07
    à¹īà¸Ńà¸ĩ
    -0.07
    æĽĩ
    -0.07
    Ñħоди
    -0.07
    罪éŃģ
    -0.07
    åīįåIJİçļĦ
    -0.07
     staged
    -0.07
    POSITIVE LOGITS
    è¾¹
    0.12
     edge
    0.10
    è¾¹çļĦ
    0.09
    éĤĬ
    0.09
     boundary
    0.08
    è¾¹çķĮ
    0.08
    è¾¹ä¸Ĭ
    0.08
    è¾¹æ¡Ĩ
    0.08
    è¾¹ç¼ĺ
    0.08
    éĤĬç·£
    0.07
    Activations Density 0.028%

    No Known Activations