© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27933
    Prev
    Next
    INDEX
    Explanations

    percentages and fractions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å¤ĸç±į
    -0.09
     dá»±ng
    -0.09
    ç¯Ļ
    -0.09
    çĸ¯çĭĤ
    -0.08
    æľīçļĦ
    -0.08
    åħļçļĦ
    -0.08
    æł¼å°Ķ
    -0.08
    çĽ¯
    -0.08
     frank
    -0.08
    åħļçļĦ建设
    -0.08
    POSITIVE LOGITS
    éĢ¾
    0.09
    leck
    0.09
     Participation
    0.09
    igits
    0.08
    åįłæ¯Ķ
    0.08
    apot
    0.08
    仲
    0.08
    çķ¥æľī
    0.08
    Markdown
    0.08
     quoi
    0.08
    Activations Density 0.254%

    No Known Activations