© 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. 46718
    Prev
    Next
    INDEX
    Explanations

    focusing on distance

    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
    ontre
    -0.08
    hia
    -0.07
    ompiler
    -0.07
    double
    -0.07
    inions
    -0.07
    eiter
    -0.07
    alaria
    -0.07
    compiler
    -0.07
     Kapol
    -0.07
     aromat
    -0.07
    POSITIVE LOGITS
    宾
    0.08
    æĤ£
    0.07
     relaxed
    0.07
    ubin
    0.07
    æijĩ
    0.07
    ä¸ĭ乡
    0.06
     corrected
    0.06
    holm
    0.06
    å°Ħ
    0.06
    otto
    0.06
    Activations Density 0.002%

    No Known Activations