© 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. 15689
    Prev
    Next
    INDEX
    Explanations

    Chrysler and copyright information

    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
    oit
    -0.19
    èį¯æĿIJ
    -0.18
    ÑĥÑĪ
    -0.18
    atar
    -0.17
    justice
    -0.17
    ative
    -0.17
    ihad
    -0.17
    еÑĢиал
    -0.17
    etre
    -0.17
    ÑĨов
    -0.16
    POSITIVE LOGITS
    ç³Ĭ
    0.18
    åİŁæĿ¥çļĦ
    0.18
    nee
    0.17
    à¹Į
    0.17
    æľīéĻIJåħ¬åı¸
    0.17
    çĦ¶æĺ¯
    0.17
    antine
    0.16
    å°±å¦ĤåIJĮ
    0.16
    anks
    0.16
    客æĪ·æıIJä¾Ľ
    0.16
    Activations Density 0.001%

    No Known Activations