© 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. 35832
    Prev
    Next
    INDEX
    Explanations

    senior positions and roles

    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
    çŃĿ
    -0.10
    æĢ§å¼º
    -0.10
    åŁİåİ¿
    -0.10
     ÐłÐ°Ñģ
    -0.10
    çĸ¯
    -0.10
    ãĤĤãģ¡
    -0.09
    丰å¯ĮçļĦ
    -0.09
    çıĻ
    -0.09
    ä¸ŃæľŁ
    -0.09
    丰å¯Į
    -0.09
    POSITIVE LOGITS
    åľ°ä½į
    0.08
    èĢģçīĮ
    0.08
    妪
    0.08
     LDS
    0.08
    æĤī
    0.08
    prises
    0.08
    æĪĸå¤ļ
    0.07
     rus
    0.07
    å¯Ĥ
    0.07
    chor
    0.07
    Activations Density 0.034%

    No Known Activations