© 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. 53557
    Prev
    Next
    INDEX
    Explanations

    after 'As' or 'Because' or 'Although' or 'Even' or 'If' or 'All' or 'Getting' or 'The' or 'This'

    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
    ä½Ĩå®ĥ
    -0.12
    ãģĿãģ®å¾Į
    -0.12
    ãģĿãĤĮãĤĴ
    -0.11
    ä½Ĩä»ĸ
    -0.11
    åIJĮæŶè¿ĺ
    -0.11
    ä½Ĩä»ĸ们
    -0.11
    ä¹ŁåĽłæѤ
    -0.11
    ä¹Łåı¯èĥ½
    -0.10
    åIJĮæĹ¶ä¹Ł
    -0.10
    ä½Ĩå®ŀéĻħä¸Ĭ
    -0.10
    POSITIVE LOGITS
    oretical
    0.10
    orem
    0.10
    odore
    0.08
    ying
    0.08
    dit
    0.08
    <![
    0.08
    inding
    0.08
    oret
    0.08
    ä¹İ
    0.07
    说åĪ°
    0.07
    Activations Density 0.769%

    No Known Activations