© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12628
    Prev
    Next
    INDEX
    Explanations

    words starting with 'ook' or 'oo'

    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
    äºĨä¸Ģåı¥
    -0.17
    eur
    -0.17
    cents
    -0.17
    lider
    -0.16
    éĻIJ度
    -0.16
    ignal
    -0.16
    çĿĽ
    -0.16
    qing
    -0.16
    Hair
    -0.15
    Began
    -0.15
    POSITIVE LOGITS
    ackers
    0.19
    strap
    0.18
    ade
    0.18
    æĪIJ为ä¸Ģ个
    0.18
    éĻ¬
    0.17
    ãĤĵãģ©
    0.17
     Morr
    0.16
    åIJ¦
    0.16
    eral
    0.16
    ERM
    0.16
    Activations Density 0.001%

    No Known Activations