© 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. 21005
    Prev
    Next
    INDEX
    Explanations

    ions and metal binding

    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
    åIJ¦
    -0.08
    âĢ¦I
    -0.08
    °F
    -0.07
    åIJīæĸ¯
    -0.07
    âĢ¦the
    -0.07
    äºĽ
    -0.07
    æ°ı
    -0.07
    ä¸į缸åIJĮ
    -0.07
    âĢ¦it
    -0.07
    ãĢįãģ¨
    -0.07
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.10
    /'
    0.09
    estig
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    и
    0.08
    ลฯ
    0.08
    или
    0.08
    /-
    0.07
    ãĢģ“
    0.07
    /$
    0.07
    Activations Density 0.019%

    No Known Activations