© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11746
    Prev
    Next
    INDEX
    Explanations

    limited edition

    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
     занÑıÑĤ
    -0.19
     па
    -0.19
    bose
    -0.18
     agon
    -0.18
    羡
    -0.18
    ×Ķת
    -0.17
    âĮĤ
    -0.17
    æĸĹå¿Ĺ
    -0.17
    bjerg
    -0.17
     дейÑģÑĤвиÑı
    -0.17
    POSITIVE LOGITS
    éĻIJéĩı
    0.35
    éĽªèĬ±
    0.23
    ç¨Ģ缺
    0.23
    æķ°éĩı
    0.22
    åĵģç§į
    0.22
    Stamp
    0.22
    çī¹åĪ«
    0.21
    Limited
    0.21
    edition
    0.21
     Barcl
    0.20
    Activations Density 0.023%

    No Known Activations