© 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. 879
    Prev
    Next
    INDEX
    Explanations

    creative teams, non-fiction, expression, modes

    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
    /her
    -0.09
    æł¹æľ¬
    -0.08
    æĥij
    -0.08
    Rnd
    -0.08
    ç¾¹
    -0.08
    ä¸Ģ级
    -0.08
    ãģ£ãģįãĤĬ
    -0.08
    Replacement
    -0.08
    cu
    -0.08
    iten
    -0.08
    POSITIVE LOGITS
    -minded
    0.12
    æĢ»çĽij
    0.11
    åįģ足
    0.10
    liest
    0.10
    otle
    0.09
    èģĶ社
    0.09
     kinky
    0.09
    ä¸İæŶ
    0.08
    åŀĭä¼ģä¸ļ
    0.08
    aira
    0.08
    Activations Density 0.007%

    No Known Activations