© 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. 9778
    Prev
    Next
    INDEX
    Explanations

    are here

    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
    cola
    -0.09
    asco
    -0.09
    ç±į
    -0.09
    urse
    -0.08
    utos
    -0.08
    anson
    -0.08
    reso
    -0.08
    åıģ
    -0.08
    æĤĦ
    -0.08
    æĬ¬
    -0.08
    POSITIVE LOGITS
    身为
    0.11
    æīįæĺ¯çľŁæŃ£
    0.11
    ulu
    0.10
    失
    0.09
    ä½łçİ°åľ¨
    0.09
    ãĥ¼ãĥĹ
    0.09
    åıĹéĤĢ
    0.09
     tù
    0.09
    iever
    0.08
    æĺ¯ä¸Ģä½į
    0.08
    Activations Density 0.058%

    No Known Activations