© 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. 17073
    Prev
    Next
    INDEX
    Explanations

    protective layer, sheet, coating, barrier

    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
    spot
    -0.22
    à¹Ģà¸Ĺศà¸ģา
    -0.21
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.20
    æĥ¯
    -0.19
    èĵ¬åĭĥ
    -0.19
     à¸ŀฤษ
    -0.19
    idious
    -0.19
    à¸Ħà¸ĵะà¸ģรรม
    -0.18
     à¹Ģมษ
    -0.18
    à¹Ĥรà¸ĩà¸ŀยา
    -0.18
    POSITIVE LOGITS
    [tmp
    0.18
    ez
    0.16
    anca
    0.16
    æŬ
    0.16
    强硬
    0.15
    rary
    0.15
    /gpl
    0.15
    rior
    0.15
    ongan
    0.15
    cks
    0.15
    Activations Density 0.010%

    No Known Activations