© 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. 47657
    Prev
    Next
    INDEX
    Explanations

    managing partner or director

    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
    icy
    -0.09
    使çĶ¨æĿĥ
    -0.09
     Hass
    -0.08
    cape
    -0.08
    kiem
    -0.08
    arium
    -0.08
    çĿ¢
    -0.08
    éģŃ
    -0.08
    aler
    -0.08
    çķı
    -0.08
    POSITIVE LOGITS
    æł¹æį®èĩªå·±
    0.11
    è¿Ļä¸ĢåĪĩ
    0.11
    èIJ¥
    0.10
    çĩŁ
    0.10
    æĴŃæĬ¥
    0.10
    ани
    0.10
    åĽŀäºĭ
    0.10
    æĬĢå¸Ī
    0.09
    .ret
    0.09
    oga
    0.09
    Activations Density 0.007%

    No Known Activations