© 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. 27957
    Prev
    Next
    INDEX
    Explanations

    help and support

    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
    ä¿ĺ
    -0.11
    æŀŃ
    -0.09
    æģ¯
    -0.09
    å½¹
    -0.09
    罡
    -0.09
    elder
    -0.09
    .undo
    -0.09
    æħĪåĸĦ
    -0.09
    æ±²åıĸ
    -0.09
    顺åºĶ
    -0.08
    POSITIVE LOGITS
    æĶ¯æı´
    0.18
    æı´
    0.17
    æĶ¯æĮģåĬĽåº¦
    0.15
    çļĦæĶ¯æĮģ
    0.14
    æĶ¯æĮģ
    0.14
     support
    0.13
    å¤ĸæı´
    0.13
    æı´åĬ©
    0.13
     reinforcements
    0.12
    åĪ°æĿ¥
    0.12
    Activations Density 0.059%

    No Known Activations