© 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. 20787
    Prev
    Next
    INDEX
    Explanations

    in the state

    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
    inness
    -0.09
     наб
    -0.09
    æĭħå½ĵ
    -0.09
    Ø´ÙĤ
    -0.08
    åıijå±ķ
    -0.08
    éĿŀ常çļĦ
    -0.08
    举
    -0.08
    éļ½
    -0.08
    æİ©çĽĸ
    -0.08
    å®ŀçĶ¨
    -0.08
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.11
    ä¸Ģ声
    0.10
    å¸ĺ
    0.09
     кÑĢоме
    0.09
    è®¤çľŁåŃ¦ä¹ł
    0.08
    åIJİæŀľ
    0.08
    ä¸Ģ头
    0.08
    è¹²
    0.08
     arguably
    0.08
    纷
    0.08
    Activations Density 0.110%

    No Known Activations