© 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. 17022
    Prev
    Next
    INDEX
    Explanations

    sports action verbs

    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
    .pin
    -0.20
    endale
    -0.19
    viz
    -0.18
    utm
    -0.18
    mans
    -0.18
    æĬ½åĩº
    -0.18
    beck
    -0.18
    å£ķ
    -0.18
    çī¹éĤĢ
    -0.18
    dock
    -0.18
    POSITIVE LOGITS
    å£ģ纸
    0.20
    åĽŀåºĶ
    0.20
    mue
    0.19
    inherits
    0.19
    交æĺĵå¹³åı°
    0.18
    ä¸Ģæŀļ
    0.18
    示èĮĥåŁºåľ°
    0.18
    (:,:,
    0.17
    æİ¥è¿ĩ
    0.17
     gegen
    0.17
    Activations Density 0.003%

    No Known Activations