© 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. 46631
    Prev
    Next
    INDEX
    Explanations

    geometry and shape descriptions

    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
    asley
    -0.08
     splice
    -0.08
    arro
    -0.07
    ipur
    -0.07
    碱æĢ§
    -0.07
    boden
    -0.07
    串èģĶ
    -0.07
    _docs
    -0.07
    çģĮ
    -0.07
    楼å±Ĥ
    -0.07
    POSITIVE LOGITS
     convex
    0.10
     bounding
    0.09
    LOS
    0.09
    Bounding
    0.08
     enclosing
    0.08
    bounding
    0.08
    çķĮ
    0.08
    åĩ¸
    0.08
     complementary
    0.08
    åĨħæµĭ
    0.07
    Activations Density 0.007%

    No Known Activations