© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12614
    Prev
    Next
    INDEX
    Explanations

    'm going

    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
    éĿŀ常é«ĺ
    -0.20
    лÑij
    -0.20
    æŀģ为
    -0.19
    éĵ®
    -0.18
     BOTH
    -0.18
    _EM
    -0.18
    VERY
    -0.18
    è¦ĭç©įãĤĤãĤĬ
    -0.18
    å¥Ħ
    -0.18
    éªļ
    -0.18
    POSITIVE LOGITS
    æ¯ķç«Ł
    0.34
    åıįæŃ£
    0.27
    æ¯ķç«Łæĺ¯
    0.26
    æľ¬æĿ¥å°±
    0.25
     anyway
    0.25
    æľ¬æĿ¥
    0.23
     otherwise
    0.23
    çķĻ
    0.22
    çķ¢ç«Ł
    0.20
    lier
    0.20
    Activations Density 0.046%

    No Known Activations