© 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. 47581
    Prev
    Next
    INDEX
    Explanations

    adolescent health and behavior

    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
    侬
    -0.10
    è¹Ī
    -0.09
    istro
    -0.09
    åįĩåįİ
    -0.09
    اث
    -0.09
    Unnamed
    -0.09
    æ·±æĥħ
    -0.08
    ãģĩ
    -0.08
    ifdef
    -0.08
    veillance
    -0.08
    POSITIVE LOGITS
    iates
    0.11
    cents
    0.09
    sWith
    0.09
    ively
    0.09
    acco
    0.08
    nak
    0.08
    ç¾Ķ
    0.08
    çĶ¨åĵģ
    0.08
    ira
    0.08
    iegel
    0.08
    Activations Density 0.007%

    No Known Activations