© 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. 32885
    Prev
    Next
    INDEX
    Explanations

    continued + ongoing actions

    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
    arded
    -0.10
    ä¸Ģåı¥è¯Ŀ
    -0.09
    çļĦæķ´ä½ĵ
    -0.09
    äºĭæĥħ
    -0.09
    æĪIJäºĨ
    -0.09
    imestamp
    -0.09
    é¢Ŀ
    -0.08
    å¼ıçļĦ
    -0.08
    lah
    -0.08
    éĵŃè®°
    -0.08
    POSITIVE LOGITS
    è¾į
    0.09
    é£ķ
    0.09
    voor
    0.09
    é«ĺ涨
    0.09
    é¹Ĭ
    0.09
     success
    0.09
    åıįå¤į
    0.09
    usal
    0.09
    åĵļ
    0.09
    éĤ¦
    0.09
    Activations Density 0.041%

    No Known Activations