© 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. 36829
    Prev
    Next
    INDEX
    Explanations

    legal case filings and 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
    æ»´
    -0.10
     Dro
    -0.10
    åĪ¨
    -0.09
     dum
    -0.09
    æľ¬äºº
    -0.09
    éĻįåĪ°
    -0.09
    å²Ľ
    -0.09
    igrated
    -0.09
    æĹºçĽĽ
    -0.08
    æ³ħ
    -0.08
    POSITIVE LOGITS
    çīµ
    0.10
    åķĥ
    0.09
    ivic
    0.09
     Haram
    0.09
    åıĹçIJĨ
    0.09
    æľĢåĸľæ¬¢çļĦ
    0.09
    æīĵèµ¢
    0.08
    omer
    0.08
     RSVP
    0.08
    åĽ½åĬ¡éĻ¢
    0.08
    Activations Density 0.262%

    No Known Activations