© 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. 43397
    Prev
    Next
    INDEX
    Explanations

    prove/confirm mathematical statements

    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
    wyn
    -0.08
    çĽijåĪ¶
    -0.08
    縼
    -0.07
    åįģä¹Ŀç«ł
    -0.07
    æĸ¹æ¡Ī设计
    -0.07
     aromat
    -0.07
    æľ¬æ¥¼
    -0.07
    绣ä¸Ģå®īæİĴ
    -0.07
    èħ¾ç©º
    -0.07
     metavar
    -0.07
    POSITIVE LOGITS
    è¯ģæĺİ
    0.09
     confirm
    0.08
    åĪ¤æĸŃ
    0.08
    çIJĨçĶ±
    0.08
    åĪ¤å®ļ
    0.08
     confirming
    0.08
     proofs
    0.08
     подÑĤвеÑĢжда
    0.08
     characterization
    0.08
    è©ķ価
    0.08
    Activations Density 0.042%

    No Known Activations