© 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. 38005
    Prev
    Next
    INDEX
    Explanations

    elective surgery

    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
    (bp
    -0.09
    ä¸IJ
    -0.09
     cup
    -0.09
    nel
    -0.08
    halt
    -0.08
     Jeb
    -0.08
     Diy
    -0.08
    ä»ħ次äºİ
    -0.08
    awa
    -0.08
    称
    -0.08
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.11
    æĶ¾è¿Ľ
    0.10
    寮
    0.10
     either
    0.10
    Either
    0.09
    ç¼¥
    0.09
    åĨ¢
    0.09
     Makeup
    0.09
    å¾ģä¿¡
    0.08
     MARK
    0.08
    Activations Density 0.011%

    No Known Activations