© 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. 50502
    Prev
    Next
    INDEX
    Explanations

    formalities and specific items

    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
    orny
    -0.11
    åĴĤ
    -0.09
    /or
    -0.09
    ings
    -0.09
    åĪĨæѧ
    -0.09
    æĶ¸
    -0.09
    大è¡Ĺ
    -0.09
    æĢı
    -0.09
    ä»»
    -0.09
    baugh
    -0.09
    POSITIVE LOGITS
    invoke
    0.09
    æĺ¯è°ģ
    0.09
    ãģĦãĤĭ
    0.09
    æĺ¯ä¸įä¼ļ
    0.08
    åıijå±ķ空éĹ´
    0.08
    æŃ¤é¡¹
    0.08
    ayer
    0.08
    à¸ģาร
    0.08
    æĺ¯ä»İ
    0.08
    ãĥIJãĥ³
    0.08
    Activations Density 0.020%

    No Known Activations