© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15945
    Prev
    Next
    INDEX
    Explanations

    Spina Bifida, browse thread, scanned-page, sequence of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    褥
    -0.20
    ä¼ĹæīĢ
    -0.20
    çīĪæĿĥ声æĺİ
    -0.20
    å¥ĸåѦ
    -0.19
    èĬľ
    -0.18
    Sender
    -0.17
    ests
    -0.17
    utter
    -0.17
    opper
    -0.17
     Skeleton
    -0.17
    POSITIVE LOGITS
    éħ¹
    0.20
    _ABI
    0.19
    rame
    0.19
    æį§
    0.18
    æľī两个
    0.18
     grade
    0.18
    åĨµ
    0.18
    itters
    0.17
    åĿIJ
    0.17
    æĢª
    0.17
    Activations Density 0.002%

    No Known Activations