© 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. 33958
    Prev
    Next
    INDEX
    Explanations

    embryo, embryological, germinate

    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
    çī¹éĴ¢
    -0.08
    éĵĿä¸ļ
    -0.08
    imia
    -0.08
    umbang
    -0.07
    ylist
    -0.07
    æľ¬æĢ§
    -0.07
    ersch
    -0.07
    IOS
    -0.07
    unge
    -0.07
    éĢĢä¼ijåIJİ
    -0.07
    POSITIVE LOGITS
    èĥļ
    0.10
     embryo
    0.10
    åıĹç²¾åįµ
    0.10
     viability
    0.10
    åıijèĤ²
    0.09
    èĥļèĥİ
    0.09
     embryos
    0.09
     dorm
    0.08
     viable
    0.08
    åıĹç²¾
    0.08
    Activations Density 0.030%

    No Known Activations