© 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. 32814
    Prev
    Next
    INDEX
    Explanations

    expressions of confusion

    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
    æĥ³åĪ°
    -0.10
    ç©¿æĪ´
    -0.10
    éĩı
    -0.09
    çħ§æĸĻ
    -0.09
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    -0.09
    ãģ¤ãĤĤãĤĬ
    -0.09
    鼶ç¢İ
    -0.09
    èĿĩ
    -0.08
    èĻŀ
    -0.08
    ä¸įä¼ļåĨį
    -0.08
    POSITIVE LOGITS
    ä¸į解
    0.16
    èĮ«çĦ¶
    0.15
    åĽ°æĥij
    0.13
    è¿·èĮ«
    0.13
    æĩµ
    0.12
    çĸijéĹ®
    0.12
    horn
    0.11
     недо
    0.11
    çĸijæĥij
    0.11
     confusion
    0.11
    Activations Density 0.059%

    No Known Activations