© 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. 10417
    Prev
    Next
    INDEX
    Explanations

    creative commons licenses and terms

    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
    çĻ½æ²Ļ
    -0.24
    inh
    -0.21
    ç¬ĭ
    -0.19
    è°Ł
    -0.19
    ä¸įéĻIJ
    -0.18
    OE
    -0.18
    ä¸įçĶ±
    -0.17
     Yao
    -0.17
    att
    -0.17
    oe
    -0.17
    POSITIVE LOGITS
    é«»
    0.20
    æĮ½
    0.20
    zman
    0.18
    estre
    0.18
    é¦Ĩ
    0.18
    æļ§
    0.17
    çŀ©çĽ®
    0.17
    (Equal
    0.17
    [Double
    0.17
    VICE
    0.17
    Activations Density 0.007%

    No Known Activations