© 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. 40201
    Prev
    Next
    INDEX
    Explanations

    nomad, pastoral, tribal, peasant

    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
    ULE
    -0.10
    raries
    -0.09
    æīĵçĿĢ
    -0.09
    è¶Ĭ
    -0.09
    çĥĽ
    -0.09
    çĶ¨å·¥
    -0.09
    åħ³çĪ±
    -0.09
    onis
    -0.09
    inality
    -0.08
     обÑģлÑĥжива
    -0.08
    POSITIVE LOGITS
    åĩºèº«
    0.09
    icas
    0.09
    çĶŁæ´»åľ¨
    0.09
    为主çļĦ
    0.09
    士
    0.09
    era
    0.08
    买车
    0.08
    çģŃ
    0.08
     bench
    0.08
     Bench
    0.08
    Activations Density 0.031%

    No Known Activations