© 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. 31798
    Prev
    Next
    INDEX
    Explanations

    hence

    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
     pros
    -0.10
    èĶĵ
    -0.09
     EITHER
    -0.09
    Pros
    -0.09
    åħĨ
    -0.09
     either
    -0.09
    either
    -0.09
     Shr
    -0.09
     Pros
    -0.09
    楣
    -0.09
    POSITIVE LOGITS
    为åķ¥
    0.11
    æīįä¼ļ
    0.10
    为ä»Ģä¹Ī
    0.10
    产çĶŁäºĨ
    0.10
    为ä½ķ
    0.10
    æīįæľī
    0.09
    çĤºä»Ģ麼
    0.09
    å°±æľīäºĨ
    0.09
    è½»æĿ¾
    0.08
    æľĢåĪĿçļĦ
    0.08
    Activations Density 0.047%

    No Known Activations