© 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. 38002
    Prev
    Next
    INDEX
    Explanations

    percentile and quartiles

    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
    ennen
    -0.07
    ä¸įè¡°
    -0.07
    æıĸ
    -0.06
    à¸ģระ
    -0.06
    oggle
    -0.06
    FIELDS
    -0.06
    è¿Ļé¢Ĺ
    -0.06
    ä¸Ń转
    -0.06
    ijk
    -0.06
    baugh
    -0.06
    POSITIVE LOGITS
     percentile
    0.10
     dá»ijc
    0.08
    éĹ¨æ§Ľ
    0.08
    illant
    0.08
    edian
    0.07
    å±Ī
    0.07
     lạnh
    0.07
    åı·ä»¤
    0.07
    acci
    0.07
    reshold
    0.07
    Activations Density 0.010%

    No Known Activations