© 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. 18279
    Prev
    Next
    INDEX
    Explanations

    think through, rethink, reasoned, foresee

    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
    èIJ¼
    -0.09
    åĽŀ头çľĭ
    -0.09
    developer
    -0.09
    åįĬ个æľĪ
    -0.08
    .encoding
    -0.08
    ickets
    -0.08
    é«ĺæīĭ
    -0.08
    encoding
    -0.08
    åĩłåĪĨéĴŁ
    -0.08
    庶
    -0.08
    POSITIVE LOGITS
    åı¯æĥ³
    0.09
     Kong
    0.09
    æŀģèĩ´
    0.09
    å½¼
    0.09
    æ¸ħæ¥ļ
    0.09
    æijĬ
    0.09
    ä¸Ģ件äºĭæĥħ
    0.09
    çĻ«
    0.09
    å¤ĸå½¢
    0.08
    opor
    0.08
    Activations Density 0.012%

    No Known Activations