© 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. 4487
    Prev
    Next
    INDEX
    Explanations

    laws or legal contexts

    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
    é¼IJ
    -0.10
    å¾Ĺ罪
    -0.10
    åħ¥åı£
    -0.09
    åı¯æݧ
    -0.09
    åĩºå±Ģ
    -0.09
    ç«Ļéķ¿
    -0.08
    è¿Ļè¾ĪåŃIJ
    -0.08
    é»ı
    -0.08
    blr
    -0.08
    æīĭä¸ŃçļĦ
    -0.08
    POSITIVE LOGITS
    _FAR
    0.10
    å®ı大
    0.09
    zig
    0.09
    篱
    0.09
    ince
    0.08
    restriction
    0.08
    好å¥ĩ
    0.08
    溯æºIJ
    0.08
     обо
    0.08
    inqu
    0.08
    Activations Density 0.049%

    No Known Activations