© 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. 32808
    Prev
    Next
    INDEX
    Explanations

    graphite electrodes and carbon materials

    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
    åĴĮçľģ
    -0.08
    ilar
    -0.08
    èģĶæĴŃ
    -0.07
     isNew
    -0.07
    lier
    -0.07
    ingly
    -0.07
    çĢij
    -0.07
    é·¹
    -0.06
     errs
    -0.06
    ials
    -0.06
    POSITIVE LOGITS
    çĤŃ
    0.12
    coal
    0.11
    carbon
    0.10
    çħ¤
    0.10
    çŁ³å¢¨
    0.09
     coal
    0.09
    碳
    0.09
    æĹłçĥŁ
    0.09
     charcoal
    0.09
    /black
    0.09
    Activations Density 0.038%

    No Known Activations