© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10222
    Prev
    Next
    INDEX
    Explanations

    stems from 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
     вÑĭбÑĢ
    -0.09
    åıĪæĺ¯
    -0.09
    è¿ĽæĿ¥
    -0.08
    craft
    -0.08
     лÑİбой
    -0.08
    indy
    -0.08
    èĭĮ
    -0.08
     diá»ħn
    -0.08
    çĬĩ
    -0.08
    åıĪ
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.18
    ä¸ī个æĸ¹éĿ¢
    0.12
    ä»Ģä¹ĪåİŁåĽł
    0.11
    åľ¨äºİ
    0.10
    ä»Ģä¹Īäºĭ
    0.10
    ä¸Ģäºĭ
    0.09
    æĪijä¸įæĥ³
    0.09
    lü
    0.09
    å¸ĮæľĽèĥ½
    0.09
    ç¡®ä¿Ŀ
    0.09
    Activations Density 0.160%

    No Known Activations