© 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. 43577
    Prev
    Next
    INDEX
    Explanations

    nature of binding or mechanism

    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
    æ¯ıéļĶ
    -0.08
     duy
    -0.07
    ç¤Ļ
    -0.07
    çİ©çļĦ
    -0.07
    multiline
    -0.07
     inconvenient
    -0.07
    num
    -0.07
    nix
    -0.07
    å¼Ģ设
    -0.07
    çĽijæĬ¤äºº
    -0.07
    POSITIVE LOGITS
    åģıåIJij
    0.09
    .partial
    0.08
    ä¸Ń庸
    0.08
    -reference
    0.07
    æŀģèĩ´
    0.07
    åĪĢåŃIJ
    0.07
    ä¸ŃæĢ§
    0.07
     stages
    0.07
     extreme
    0.07
    åįģéĩĮ
    0.07
    Activations Density 0.004%

    No Known Activations