© 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. 6185
    Prev
    Next
    INDEX
    Explanations

    goals and targets

    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
    ç½¢
    -0.10
    éģį
    -0.10
    è¿ĺæľª
    -0.10
    ä¸Ģè¶Ł
    -0.09
    奴
    -0.08
     lad
    -0.08
    gger
    -0.08
    зам
    -0.08
    æĭħå½ĵ
    -0.08
    ordo
    -0.08
    POSITIVE LOGITS
    缮æłĩ
    0.15
    åıijå±ķ缮æłĩ
    0.13
    æĮĩæłĩ
    0.12
     targets
    0.12
     goals
    0.11
    ìľ¨
    0.11
    ãĤ´ãĥ¼ãĥ«
    0.11
    缮æ¨Ļ
    0.10
     Targets
    0.10
    Goal
    0.10
    Activations Density 0.040%

    No Known Activations