© 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. 16963
    Prev
    Next
    INDEX
    Explanations

    institutions or organizations

    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
    åĦ¿
    -0.22
    ful
    -0.21
    иÑĢÑĥÑİÑī
    -0.21
    out
    -0.21
    iers
    -0.21
     retard
    -0.20
    ting
    -0.20
    룬
    -0.20
    ous
    -0.19
    less
    -0.19
    POSITIVE LOGITS
     fkk
    0.22
     taxp
    0.21
     iNdEx
    0.20
    -tm
    0.20
    agrid
    0.20
    ;element
    0.20
    uars
    0.20
    ëķľ
    0.20
    irut
    0.19
    ëºĢ
    0.19
    Activations Density 0.152%

    No Known Activations