© 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. 10680
    Prev
    Next
    INDEX
    Explanations

    ADVERTISEMENT

    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
    -ing
    -0.21
    vc
    -0.20
    缺
    -0.20
    ive
    -0.19
    vik
    -0.19
    åĥıæĺ¯
    -0.18
    opes
    -0.17
    's
    -0.17
    ing
    -0.17
     bach
    -0.17
    POSITIVE LOGITS
    å¾Īåĸľæ¬¢
    0.20
    ä¸įåĸľæ¬¢
    0.20
    è§ŀ
    0.18
    ãĤĭãģ¹ãģį
    0.18
    ADX
    0.18
    澤
    0.18
    ç«ĭãģ¦
    0.18
     XK
    0.18
    æ³
    0.17
    éĢ¶
    0.17
    Activations Density 0.097%

    No Known Activations