© 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. 8229
    Prev
    Next
    INDEX
    Explanations

    finally, at last

    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
    麾
    -0.10
    æģĥ
    -0.09
    ä¸ĢçĤ¹ä¹Łä¸į
    -0.09
    彬
    -0.09
    SWG
    -0.09
    ä½łä¸į
    -0.08
    Continue
    -0.08
    ноÑģÑĤ
    -0.08
    亿ä¸ĩ
    -0.08
    çŀĦ
    -0.08
    POSITIVE LOGITS
    ç»Īäºİ
    0.26
    çµĤæĸ¼
    0.21
     finally
    0.20
    æĢ»ç®Ĺ
    0.18
    finally
    0.17
    Finally
    0.14
    	finally
    0.14
     Finally
    0.14
    æħ¢
    0.11
    ç®Ĺæĺ¯
    0.10
    Activations Density 0.061%

    No Known Activations