© 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. 29792
    Prev
    Next
    INDEX
    Explanations

    charged, arrested, guilty, or convicted

    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
    解éĻ¤
    -0.09
    请åģĩ
    -0.09
    欢è¿İ大家
    -0.08
    éĻIJå®ļ
    -0.08
    istani
    -0.08
    åħ³èģĶ交æĺĵ
    -0.08
    æIJ¬å®¶
    -0.08
    é¦ĸ缸
    -0.08
    normal
    -0.08
    ista
    -0.08
    POSITIVE LOGITS
     ìĤ¬ìĿ´
    0.09
    ull
    0.09
    çµĤ
    0.09
    ç»Ī身
    0.09
    å¦Ĥå®ŀ
    0.09
    tru
    0.09
    isd
    0.09
    åĿ¦
    0.09
     Rip
    0.08
    /facebook
    0.08
    Activations Density 0.079%

    No Known Activations