© 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. 15950
    Prev
    Next
    INDEX
    Explanations

    copyright and rights reserved

    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
    æŁIJäºĽ
    -0.27
     некоÑĤоÑĢÑĭÑħ
    -0.22
    两项
    -0.21
    éĺ¡
    -0.20
    few
    -0.20
     algunas
    -0.20
    elves
    -0.20
    æĽ´å¤ļ
    -0.20
     vÃłi
    -0.20
    éĤ£å°±æĺ¯
    -0.19
    POSITIVE LOGITS
     except
    0.42
    except
    0.37
    Except
    0.35
     кÑĢоме
    0.32
     Except
    0.32
    åĮħæĭ¬
    0.31
     Äijá»ģu
    0.29
    _except
    0.29
     whatsoever
    0.28
     demás
    0.27
    Activations Density 0.398%

    No Known Activations