© 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. 57778
    Prev
    Next
    INDEX
    Explanations

    hydrogen bonding and interactions

    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
    麾
    -0.08
    TagName
    -0.07
    æĥ³å¾ĹåĪ°
    -0.07
    ç§ij缮
    -0.07
     Lump
    -0.07
     statist
    -0.07
     vids
    -0.07
    ilson
    -0.07
    statistics
    -0.07
    丽人
    -0.07
    POSITIVE LOGITS
    nud
    0.08
    èĺ
    0.07
    izzi
    0.07
    GX
    0.07
     reversible
    0.07
    ÙĪزÙĩ
    0.07
    åķĦ
    0.06
    annis
    0.06
    ç»´ç³»
    0.06
     cancell
    0.06
    Activations Density 0.010%

    No Known Activations