© 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. 797
    Prev
    Next
    INDEX
    Explanations

    sir,

    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
    åŃª
    -0.09
    è¿Ļ家ä¼Ļ
    -0.09
    HP
    -0.08
    使人
    -0.08
    è¿Ļ对
    -0.08
    ä¼Ļä¼´
    -0.08
    ivalent
    -0.08
    ued
    -0.08
    еÑĢÑĮ
    -0.08
    èĬĤæ°´
    -0.08
    POSITIVE LOGITS
    们çļĦ
    0.12
    ships
    0.10
    ographics
    0.10
    stone
    0.10
    SHIP
    0.09
    çĪ·
    0.09
    ä½ĽéĻĢ
    0.09
    çķľ
    0.09
    fully
    0.09
    们
    0.09
    Activations Density 0.007%

    No Known Activations