© 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. 64515
    Prev
    Next
    INDEX
    Explanations

    triangle-triangle intersection

    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
     downstairs
    -0.08
     VARIABLE
    -0.07
     upstairs
    -0.07
    KeyType
    -0.07
     slogan
    -0.07
     Pase
    -0.07
    .shuffle
    -0.06
    æĭįæīĭ
    -0.06
    choices
    -0.06
    -variable
    -0.06
    POSITIVE LOGITS
     vertices
    0.09
     travers
    0.09
     centroids
    0.08
     primitives
    0.08
     waypoints
    0.08
    å¤ļè¾¹
    0.08
     primitive
    0.08
    (vertices
    0.08
     intersect
    0.08
     centroid
    0.08
    Activations Density 0.099%

    No Known Activations