© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8825
    Prev
    Next
    INDEX
    Explanations

    prosecutors, judges, and legal proceedings

    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
    è¹ij
    -0.09
    åĨ²åĪº
    -0.09
    å¥ĸåĬ±
    -0.09
    计
    -0.09
    èĭ±éĽĦ
    -0.09
    igr
    -0.08
    è³ĵ
    -0.08
    宾
    -0.08
    ä¼ĺ
    -0.08
    ::__
    -0.08
    POSITIVE LOGITS
    衽
    0.10
    æݧ
    0.09
    ÑĥÑģÑĤ
    0.09
    æĮĩæݧ
    0.09
    æŃª
    0.09
    åįĩéĻį
    0.08
     incom
    0.08
    ä¼ı
    0.08
    wg
    0.08
    æıIJåīį
    0.08
    Activations Density 0.111%

    No Known Activations