© 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. 48932
    Prev
    Next
    INDEX
    Explanations

    legal laws

    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
    ularity
    -0.09
    çľ¼åħī
    -0.08
    å¼¼
    -0.08
     Blanch
    -0.08
    磾
    -0.08
    prung
    -0.08
    æ¿Ģ
    -0.08
    _CB
    -0.08
    çļĦçľ¼åħī
    -0.08
    塾
    -0.07
    POSITIVE LOGITS
    æ³ķå¾ĭ
    0.18
    æ³ķå¾ĭè§Ħå®ļ
    0.16
     legal
    0.14
    æ³ķå¾ĭæ³ķè§Ħ
    0.13
     laws
    0.13
    legal
    0.13
     law
    0.12
     اÙĦÙĤاÙĨÙĪÙĨ
    0.12
    æ³ķ令
    0.12
    æ³ķè§Ħ
    0.12
    Activations Density 0.142%

    No Known Activations