© 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. 62380
    Prev
    Next
    INDEX
    Explanations

    hypertrophy

    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
    ستا
    -0.08
    ç¼ļ
    -0.08
    ä¿Ŀéļľå·¥ä½ľ
    -0.08
    <small
    -0.08
    (insert
    -0.08
    ç¹°
    -0.08
    æľĢæĸ°æĽ´æĸ°
    -0.07
    åĨį说äºĨ
    -0.07
    è¾ĥå¼±
    -0.07
    Ñģпи
    -0.07
    POSITIVE LOGITS
     hypert
    0.09
    èĤ¿å¤§
    0.09
    èĤ¥å¤§
    0.08
     enlarg
    0.08
     size
    0.08
    å¢ŀçĶŁ
    0.08
     enlargement
    0.08
    å¢ŀ大
    0.08
     ì¶ķ
    0.07
     growth
    0.07
    Activations Density 0.066%

    No Known Activations