© 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. 24100
    Prev
    Next
    INDEX
    Explanations

    genome-wide association studies

    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
    åį¸ä¸ĭ
    -0.07
    åĸĤ
    -0.07
    åį¸
    -0.07
    วัย
    -0.07
    å¾ģ
    -0.07
    ä¾Ľä¸įåºĶæ±Ĥ
    -0.06
    reens
    -0.06
     ì¡°ìĦ±
    -0.06
    lator
    -0.06
    踪影
    -0.06
    POSITIVE LOGITS
    vig
    0.09
     mutl
    0.09
    ächer
    0.08
     metropolitan
    0.08
    ypy
    0.08
    çĬ¯
    0.08
     across
    0.08
    ensem
    0.07
    Across
    0.07
    ujur
    0.07
    Activations Density 0.009%

    No Known Activations