© 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. 29771
    Prev
    Next
    INDEX
    Explanations

    listing numbers with commas

    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
    åĭī
    -0.08
    åĪĽ
    -0.07
    åĪĨ许
    -0.07
    teman
    -0.07
    inian
    -0.07
    Inset
    -0.07
    åĬ²
    -0.07
    ç¤
    -0.07
    iš
    -0.07
     ÐŀбзоÑĢ
    -0.07
    POSITIVE LOGITS
    opin
    0.07
    evol
    0.06
    ser
    0.06
    ming
    0.06
    iors
    0.06
    ral
    0.06
    /or
    0.06
     rumours
    0.06
    æĮ½
    0.06
    rale
    0.06
    Activations Density 0.016%

    No Known Activations