© 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. 16781
    Prev
    Next
    INDEX
    Explanations

    residents of

    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
    Ñīи
    -0.11
    eries
    -0.11
    -0.11
    ìį¨
    -0.11
    sters
    -0.10
    å´½
    -0.10
    /she
    -0.10
    åĪĥ
    -0.09
    iness
    -0.09
    书éĿ¢
    -0.09
    POSITIVE LOGITS
    ials
    0.13
    idue
    0.11
    çĶ«
    0.10
    ãĥ³
    0.09
    çĶŁäº§æĢ»åĢ¼
    0.09
    ship
    0.09
     halls
    0.09
    chaft
    0.09
    cue
    0.09
    innen
    0.09
    Activations Density 0.020%

    No Known Activations