© 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. 54790
    Prev
    Next
    INDEX
    Explanations

    crime or incident with consequences

    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
    æĢ¯
    -0.09
    éĤ£è¾¹
    -0.09
    è³ĩ
    -0.08
    æľīä¸Ģå®ļçļĦ
    -0.08
     Scratch
    -0.08
    CFG
    -0.08
    èĸª
    -0.08
    èĥĦ
    -0.08
    åİĨ代
    -0.08
    è¡°èĢģ
    -0.08
    POSITIVE LOGITS
    æĹ¶ä»£ä¸ŃåĽ½
    0.09
    å½ĵæĹ¥
    0.09
    åįļæĸĩ
    0.09
    æĹłç¼Ŀ
    0.09
    两年åīį
    0.09
    åĽĽä½į
    0.09
    ëĭ´
    0.09
    ald
    0.09
    åıijçĶŁåľ¨
    0.09
    æĪijå½ĵæŶ
    0.09
    Activations Density 0.128%

    No Known Activations