© 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. 24955
    Prev
    Next
    INDEX
    Explanations

    chemical reactions

    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
    ivot
    -0.07
    icz
    -0.07
    istream
    -0.07
    .segment
    -0.07
    anh
    -0.07
     ÙħÙĤØ·
    -0.07
    æ·ij
    -0.07
    åįķ人
    -0.07
    山人
    -0.07
    ikal
    -0.06
    POSITIVE LOGITS
    åĮĸåѦåıįåºĶ
    0.12
     reactions
    0.12
     involving
    0.12
    åıijçĶŁåľ¨
    0.11
     occurring
    0.10
    åıįåºĶ
    0.10
    è¿ĩç¨ĭ
    0.10
     reaction
    0.10
     catal
    0.10
    æ¶īåıĬ
    0.10
    Activations Density 0.041%

    No Known Activations