© 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. 46640
    Prev
    Next
    INDEX
    Explanations

    template names and definitions

    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
    Å¡Ä·
    -0.07
     sin
    -0.06
    hm
    -0.06
    ä¸Īéĩı
    -0.06
    orso
    -0.06
     organ
    -0.06
    使çĶ¨åIJİ
    -0.06
     loose
    -0.06
    æĸ°çĶŁçļĦ
    -0.06
     organic
    -0.06
    POSITIVE LOGITS
    èĥ§
    0.09
    æ´
    0.08
    åĨ°åĨ°
    0.08
     há»ĵi
    0.08
    forte
    0.08
    wah
    0.08
    æĺİçıł
    0.08
    (expect
    0.08
    è¾Ī
    0.08
    amah
    0.08
    Activations Density 0.003%

    No Known Activations