© 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. 17178
    Prev
    Next
    INDEX
    Explanations

    HTML abbr tags

    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
     bells
    -0.21
    女æİĴ
    -0.18
    æŀģéĢŁ
    -0.18
    epoch
    -0.18
     whore
    -0.17
    æī¿è½½
    -0.17
     bell
    -0.17
    ç¿Ĭ
    -0.17
     Rookie
    -0.17
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.17
    POSITIVE LOGITS
    etas
    0.21
    ç¢İçīĩ
    0.19
    rades
    0.19
    çĽĪ
    0.18
    ä¹ĭæĹħ
    0.18
    ç»ıéªĮåĴĮ
    0.18
    -than
    0.18
     Julien
    0.18
    xec
    0.18
     ness
    0.18
    Activations Density 0.180%

    No Known Activations