© 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. 17027
    Prev
    Next
    INDEX
    Explanations

    first come first served

    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
    çľĭä¸Ģçľĭ
    -0.20
    ãģĨãģ¡
    -0.18
    -mar
    -0.18
    æĸĽ
    -0.17
     Dro
    -0.17
    enty
    -0.17
     flushing
    -0.17
    æĹ¢åı¯ä»¥
    -0.16
    AAP
    -0.16
    èĽĻ
    -0.16
    POSITIVE LOGITS
     ness
    0.19
    /or
    0.19
     other
    0.19
    ulum
    0.18
    çĸĥ
    0.18
    åİ
    0.18
    涯
    0.17
    çīĪ
    0.17
    @m
    0.17
    èĬ¬
    0.17
    Activations Density 0.079%

    No Known Activations