© 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. 19943
    Prev
    Next
    INDEX
    Explanations

    in her/their/its/his

    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
     bunch
    -0.12
    ä¸Ģ大æī¹
    -0.11
    èİĺ
    -0.09
     Madden
    -0.09
    éķ¿æľŁä»¥æĿ¥
    -0.09
    å½ķåħ¥
    -0.09
    棣
    -0.09
    ä¸Ģ大åłĨ
    -0.09
    olem
    -0.09
    ä¸Ģ群人
    -0.09
    POSITIVE LOGITS
    ä½ĵçİ°äºĨ
    0.09
    æĻ®æĥł
    0.08
    åĨįè§ģ
    0.08
    åıįæĺłäºĨ
    0.08
    æĪŁ
    0.08
     References
    0.08
    çīĴ
    0.07
    wil
    0.07
     Factory
    0.07
    å¼ķ
    0.07
    Activations Density 0.078%

    No Known Activations