© 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. 60883
    Prev
    Next
    INDEX
    Explanations

    questions, problems, issues

    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
    ä¹İ
    -0.09
    _basis
    -0.09
    ä¸įè´Ł
    -0.08
    ç«Ł
    -0.08
    arrison
    -0.08
     Kidd
    -0.08
    è¶ģçĿĢ
    -0.08
    綾
    -0.08
    好ä¸į容æĺĵ
    -0.08
    uv
    -0.08
    POSITIVE LOGITS
    åĽ°æĥij
    0.17
    åĽ°æī°
    0.16
    çŁŃæĿ¿
    0.15
    çļĦéĹ®é¢ĺ
    0.15
    éļ¾çĤ¹
    0.15
    éĹ®é¢ĺæĺ¯
    0.14
    çªģåĩºéĹ®é¢ĺ
    0.14
    éĩįéĩį
    0.14
    éĹ®é¢ĺ
    0.14
     пÑĢоблемÑĭ
    0.14
    Activations Density 0.368%

    No Known Activations