© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17184
    Prev
    Next
    INDEX
    Explanations

    entry positions

    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
    Negative Logits
    lus
    -0.21
    ACHI
    -0.18
    ths
    -0.18
    lug
    -0.17
    缼
    -0.17
    æģ°
    -0.17
    ä½Ĺ
    -0.17
    æİ¥åĬĽ
    -0.17
    éĢģæĿ¥
    -0.17
    /dat
    -0.17
    POSITIVE LOGITS
    å¥ĸ项
    0.21
    variant
    0.20
    å¹´èĸª
    0.20
    çīĪæľ¬
    0.19
    -most
    0.19
    wert
    0.18
    version
    0.18
     Fatal
    0.18
    Fatal
    0.18
    yet
    0.18
    Activations Density 0.009%

    No Known Activations