© 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. 4447
    Prev
    Next
    INDEX
    Explanations

    novel therapeutic drug

    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
    &w
    -0.09
    &T
    -0.08
    raries
    -0.08
    plorer
    -0.08
    &S
    -0.07
    ToDevice
    -0.07
    足äºĨ
    -0.07
    andra
    -0.07
    Mappings
    -0.07
    大å¹ħ度
    -0.06
    POSITIVE LOGITS
    uah
    0.08
    ish
    0.07
    åı¯æĥ³
    0.07
    illon
    0.07
    angi
    0.07
    ä»ĭäºİ
    0.07
    гÑĥ
    0.07
     <![
    0.06
    ect
    0.06
    nick
    0.06
    Activations Density 0.002%

    No Known Activations