© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63433
    Prev
    Next
    INDEX
    Explanations

    synthetic route, procedures, synthesis

    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
    享
    -0.09
    é£İæīĩ
    -0.08
    æģ¯
    -0.08
    éĺĻ
    -0.08
    æ³»
    -0.08
     thái
    -0.08
    æ½ľ
    -0.08
    æľŁå¾ħ
    -0.08
    èij¬
    -0.08
    æ¯ķ
    -0.08
    POSITIVE LOGITS
    æ¶īåıĬ
    0.10
    路线
    0.09
    æ³ķåĪ¶
    0.09
    åıįåºĶ
    0.09
    éĢĶå¾Ħ
    0.09
    éĩijéĻµ
    0.09
    overn
    0.09
    éĩľ
    0.09
    å·¥ä¸ļåĮĸ
    0.09
    æį·
    0.08
    Activations Density 0.309%

    No Known Activations