© 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. 43375
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and structures

    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
    awah
    -0.08
    asel
    -0.07
     filtered
    -0.07
    ither
    -0.07
     filtr
    -0.07
    tter
    -0.07
    Filtered
    -0.07
    å¾ĺå¾Ĭ
    -0.07
    宾
    -0.07
     stale
    -0.07
    POSITIVE LOGITS
    å½¢çĬ¶
    0.16
    å½¢çĬ¶çļĦ
    0.14
     shape
    0.14
    çļĦå¤ĸå½¢
    0.13
    尺寸
    0.13
     shapes
    0.13
    çļĦå½¢çĬ¶
    0.13
    å¤ĸå½¢
    0.12
    å½¢ä½ĵ
    0.12
    å½¢çĭĢ
    0.12
    Activations Density 0.176%

    No Known Activations