© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60728
    Prev
    Next
    INDEX
    Explanations

    commas followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    çīĽ
    -0.10
    æĭĨ
    -0.10
    lett
    -0.09
    骥
    -0.09
    è®°ä½ı
    -0.09
    _ENDPOINT
    -0.09
    並ä¸Ķ
    -0.09
    éĩľ
    -0.09
    ìĬ¬
    -0.09
    \Request
    -0.09
    POSITIVE LOGITS
    2
    0.11
    0
    0.10
    1
    0.10
    4
    0.10
    8
    0.09
    常è¯Ĩ
    0.09
    3
    0.09
    7
    0.09
    ollen
    0.09
    6
    0.09
    Activations Density 0.127%

    No Known Activations