© 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. 40205
    Prev
    Next
    INDEX
    Explanations

    ranching and rodeo terms

    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
    饱
    -0.10
    å¹³åĿ¦
    -0.09
    ä¸įè¿ĩæĺ¯
    -0.09
    dash
    -0.09
    asje
    -0.09
    åı¸æľº
    -0.08
    éªĬ
    -0.08
    utow
    -0.08
    èĤĨ
    -0.08
    éĺį
    -0.08
    POSITIVE LOGITS
    çĸ³
    0.09
    认
    0.09
    èĥļ
    0.09
    æ°¸
    0.09
    åħį
    0.08
    _variance
    0.08
    ç¿¡ç¿ł
    0.08
    ç¾İæĸ¹
    0.08
    å¼ģ
    0.08
    诰
    0.08
    Activations Density 0.089%

    No Known Activations