© 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. 16907
    Prev
    Next
    INDEX
    Explanations

    rounding to 0 dps

    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
    olé
    -0.08
    ewa
    -0.08
    ĮĢ
    -0.08
    igl
    -0.07
    åIJĪä½ľçĶ¨
    -0.07
    θÎŃ
    -0.07
    awy
    -0.07
    ecter
    -0.07
    临åºĬçĹĩçĬ¶
    -0.07
    anh
    -0.07
    POSITIVE LOGITS
     unity
    0.07
    æĺ¯ä¸Ģé¢Ĺ
    0.07
     (=
    0.06
    st
    0.06
     =
    0.06
    éĢļ天
    0.06
     i
    0.06
    xffffffff
    0.05
    æĺİæľĹ
    0.05
    红è±Ĩ
    0.05
    Activations Density 0.006%

    No Known Activations