© 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. 23221
    Prev
    Next
    INDEX
    Explanations

    definite or indefinite

    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
    zinho
    -0.09
    åħIJ
    -0.09
    åħ¢åħ¢ä¸ļä¸ļ
    -0.08
    گز
    -0.08
    lebnis
    -0.08
    firma
    -0.08
    ings
    -0.08
    abouts
    -0.08
    alisi
    -0.07
    cule
    -0.07
    POSITIVE LOGITS
    emente
    0.09
    resse
    0.08
    ional
    0.08
    orno
    0.08
    CTION
    0.08
    kannya
    0.08
    /manual
    0.08
    尼迪
    0.07
    AGR
    0.07
    GREE
    0.07
    Activations Density 0.008%

    No Known Activations