© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9044
    Prev
    Next
    INDEX
    Explanations

    hide and seek

    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
    åħ±åIJĮä½ĵ
    -0.10
    件äºĭ
    -0.09
    åľī
    -0.09
    åŃĢ
    -0.09
    éĵ¨
    -0.08
    æľIJ
    -0.08
    ä¸ĭä¾Ĩ
    -0.08
     spont
    -0.08
    樯
    -0.08
    åıijå±ķæĪĺçķ¥
    -0.08
    POSITIVE LOGITS
    hill
    0.12
    ughter
    0.10
    аÑĤелÑĮ
    0.09
    ÑĪе
    0.09
    éĻIJãĤĬ
    0.09
    å¸Ŀ
    0.09
    oley
    0.08
    ä½łæĺ¯
    0.08
    atoon
    0.08
    biz
    0.08
    Activations Density 0.011%

    No Known Activations