© 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. 10479
    Prev
    Next
    INDEX
    Explanations

    in contrast

    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
     tầm
    -0.20
    ideo
    -0.17
    éłĤãģį
    -0.17
    _Struct
    -0.17
    ç½ij讯
    -0.17
    Toolkit
    -0.17
     tjejer
    -0.17
    袢
    -0.17
    èĤłèĥĥ
    -0.17
    åĴ¨è¯¢æľįåĬ¡
    -0.17
    POSITIVE LOGITS
     ведÑĮ
    0.24
    ä¹Łä¸įä¾ĭå¤ĸ
    0.19
     unsur
    0.19
    åį³
    0.19
    åį³æĺ¯
    0.18
    åĽłåľ°
    0.18
    汶
    0.18
    emin
    0.18
    ILES
    0.18
    åĩĨ
    0.18
    Activations Density 0.358%

    No Known Activations