© 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. 5844
    Prev
    Next
    INDEX
    Explanations

    legal or law-related context

    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
    ç¾
    -0.08
     prescriptions
    -0.08
    æĪijçŁ¥éģĵ
    -0.08
    é¢Ħç®Ĺ
    -0.08
    åľ¨æĪij
    -0.08
    obel
    -0.08
    éĩĬæĶ¾
    -0.08
    箧
    -0.08
     pil
    -0.07
    éĽĦ
    -0.07
    POSITIVE LOGITS
    认å®ļ
    0.14
    åĪ¤å®ļ
    0.10
    æĺ¯åIJ¦åŃĺåľ¨
    0.09
    æĪIJç«ĭ
    0.09
    è¦ģçľĭ
    0.09
    åıªè¦ģæĺ¯
    0.09
    åĪĨåī²
    0.09
    orro
    0.09
    åĽłæŀľ
    0.09
    -elements
    0.09
    Activations Density 0.053%

    No Known Activations