© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57981
    Prev
    Next
    INDEX
    Explanations

    continuous map of sets

    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
    æŃ£å¤§
    -0.09
    /sources
    -0.09
    æ´»äºĨ
    -0.08
     espé
    -0.08
    éı¡
    -0.08
    ngle
    -0.08
    rige
    -0.07
    angling
    -0.07
    _FLUSH
    -0.07
    kla
    -0.07
    POSITIVE LOGITS
    yan
    0.07
     pon
    0.07
    å¾Ģ
    0.07
    implements
    0.07
    å¿Ĺ
    0.06
    ungan
    0.06
    寿
    0.06
    andang
    0.06
    perc
    0.06
    åijĺ
    0.06
    Activations Density 0.031%

    No Known Activations