© 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. 10657
    Prev
    Next
    INDEX
    Explanations

    lupus, rally, access, luge

    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
    =Math
    -0.16
    æĢĽ
    -0.16
    _TEM
    -0.16
    Wake
    -0.15
    Interview
    -0.15
     Hiring
    -0.15
    _ARCH
    -0.15
    {{$
    -0.14
    odom
    -0.14
     Lever
    -0.14
    POSITIVE LOGITS
    buster
    0.16
     Cla
    0.15
    大èĥĨ
    0.15
    éĢĴ交
    0.15
     demi
    0.15
    orr
    0.15
     Opr
    0.15
    ught
    0.15
    ä¸ĭçıŃ
    0.14
    irts
    0.14
    Activations Density 10.537%

    No Known Activations