© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21551
    Prev
    Next
    INDEX
    Explanations

    dialogue question starters

    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
    airo
    -0.09
    acent
    -0.08
    èĩªæĿ¥
    -0.08
    åĺ±
    -0.08
    atown
    -0.08
    irro
    -0.08
     twice
    -0.08
    注æĦıçļĦæĺ¯
    -0.07
    kelijk
    -0.07
    马æĭī
    -0.07
    POSITIVE LOGITS
    ä¸įå°ij人
    0.07
    isu
    0.07
    outs
    0.06
     nou
    0.06
    rov
    0.06
    atron
    0.06
    oir
    0.06
     sen
    0.06
    墩
    0.06
    rei
    0.06
    Activations Density 0.003%

    No Known Activations