© 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. 10310
    Prev
    Next
    INDEX
    Explanations

    astronomy and astronomer

    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
    OrCreate
    -0.18
    ç¶ļ
    -0.18
    ðŁı»
    -0.17
    stock
    -0.17
    å°Ķæĸ¯
    -0.17
    çŁ¥è¯ĨåĪĨåŃIJ
    -0.16
    è´¨éĩıåĴĮ
    -0.16
    ters
    -0.16
    stead
    -0.16
    à¹ĭ
    -0.15
    POSITIVE LOGITS
    er
    0.20
    à¹Į
    0.20
    atte
    0.17
    USES
    0.17
    um
    0.17
    aight
    0.16
    SHIP
    0.16
    atum
    0.16
     audible
    0.16
    liness
    0.15
    Activations Density 0.012%

    No Known Activations