© 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. 21096
    Prev
    Next
    INDEX
    Explanations

    lawyer discipline and bar associations

    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
    é«ĺ级
    -0.09
    ä¸Ń级
    -0.09
    ä¸ĬçıŃ
    -0.09
    å½±
    -0.09
    astr
    -0.09
    éĻªçĿĢ
    -0.08
    æĴ
    -0.08
    éģĹ
    -0.08
    ä¸Ģ级
    -0.08
    æİĢ
    -0.08
    POSITIVE LOGITS
    çĤī
    0.09
     sustain
    0.09
    -cn
    0.09
     Furn
    0.08
    æģĴ
    0.08
     tarn
    0.08
     sustained
    0.08
    éĻį
    0.08
    .getComponent
    0.08
    è¤Ĵ
    0.08
    Activations Density 0.299%

    No Known Activations