© 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. 7403
    Prev
    Next
    INDEX
    Explanations

    license descriptions

    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
    æĹŃ
    -0.10
    æĪĸèĢħ说
    -0.09
    æģ°
    -0.09
    è¨ĩ
    -0.09
    åĴĮ
    -0.08
     Hyde
    -0.08
    åĴĮåħ¶ä»ĸ
    -0.08
    uite
    -0.08
     zwar
    -0.08
    akan
    -0.07
    POSITIVE LOGITS
    éĥ½æĹłæ³ķ
    0.17
    éĥ½åı¯ä»¥
    0.16
     depending
    0.16
    åĿĩåı¯
    0.15
    depending
    0.15
    éĥ½æľīçĿĢ
    0.15
     whichever
    0.15
    éĥ½ä¸įä¼ļ
    0.14
    æĢ»ä¹ĭ
    0.14
    ãģĦãģļãĤĮ
    0.14
    Activations Density 0.304%

    No Known Activations