© 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. 11100
    Prev
    Next
    INDEX
    Explanations

    below a threshold or level

    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
    æĸ°åĬłåĿ¡
    -0.11
    kson
    -0.09
    ìį¨
    -0.09
    bpp
    -0.09
    ноп
    -0.09
    ยาม
    -0.09
    jenigen
    -0.08
     Laufe
    -0.08
    ahui
    -0.08
    bish
    -0.08
    POSITIVE LOGITS
    ت
    0.10
    ../../
    0.09
    ìĦľëĬĶ
    0.09
    erk
    0.09
    Ø©
    0.09
    halb
    0.08
    gether
    0.08
    een
    0.07
    د
    0.07
    ÙħÙĩ
    0.07
    Activations Density 0.023%

    No Known Activations