© 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. 65349
    Prev
    Next
    INDEX
    Explanations

    mathematical modeling behavior

    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
     puisqu
    -0.08
    åĽłä¸ºæĪij们
    -0.07
    çĶ³æĺİ
    -0.07
    ¼
    -0.07
    æ¯ķç«Ł
    -0.07
    wali
    -0.07
    讼
    -0.06
    å§ij
    -0.06
    REW
    -0.06
    èĶĹ
    -0.06
    POSITIVE LOGITS
    èijĹåIJįçļĦ
    0.10
    æĪijè®°å¾Ĺ
    0.08
     tzv
    0.08
    æľĢèijĹåIJįçļĦ
    0.08
     famous
    0.08
     pioneered
    0.08
    icho
    0.08
    rovers
    0.08
     famously
    0.08
    æį®è¯´
    0.08
    Activations Density 0.006%

    No Known Activations