© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19032
    Prev
    Next
    INDEX
    Explanations

    unless, except

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çĶļèĩ³è¿ŀ
    -0.10
    çļĦç¡®
    -0.10
    åĽºçĦ¶
    -0.09
    鹬
    -0.09
    åİŁåĽł
    -0.09
    æĭį
    -0.08
    éħ
    -0.08
    åIJĪä¸Ģ
    -0.08
    ç»Ļä»ĸ们
    -0.08
    æĥħå½¢
    -0.08
    POSITIVE LOGITS
    fy
    0.11
    eer
    0.10
    ä½ł
    0.09
    æľī人
    0.09
    ãģĤãĤĭç¨ĭ度
    0.09
    ìŀĦ
    0.08
    obic
    0.08
    æĪĸå¤ļ
    0.08
     someone
    0.08
    ICES
    0.08
    Activations Density 0.025%

    No Known Activations