© 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. 26130
    Prev
    Next
    INDEX
    Explanations

    situation or status

    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
    -0.10
    乡
    -0.09
    èĢģçĻ¾å§ĵ
    -0.09
    æī«ä¸Ģæī«
    -0.09
    åħĪæĬĬ
    -0.09
    ndon
    -0.08
    åºĵéĩĮ
    -0.08
    ä¹Łå¥½
    -0.08
    log
    -0.08
    ниÑĩ
    -0.08
    POSITIVE LOGITS
    å¾Ĺ天çĭ¬åİļ
    0.10
    å¤ļæĸ¹
    0.09
    åīį身
    0.08
    è¿Ķ
    0.08
     Bret
    0.08
    çŁĽçĽ¾
    0.08
    _ENC
    0.08
    æĪIJç«ĭ以æĿ¥
    0.08
    åIJĦæĸ¹
    0.08
    isphere
    0.08
    Activations Density 0.034%

    No Known Activations