© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22059
    Prev
    Next
    INDEX
    Explanations

    laws against certain activities

    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
    æĺ¥è¿IJ
    -0.11
    ç½®æį¢
    -0.10
     зло
    -0.09
    è·ijéģĵ
    -0.09
    åĨ¤
    -0.09
    çĽĺ
    -0.09
    çīĮ
    -0.09
    äºĨ解åĪ°
    -0.08
    ãģ£ãģįãĤĬ
    -0.08
    corner
    -0.08
    POSITIVE LOGITS
    ç§ģèĩª
    0.10
    eme
    0.09
    æ®Ĩ
    0.09
     punishable
    0.09
    odos
    0.09
    oders
    0.09
    ä»»ä½ķ人
    0.09
     anybody
    0.09
    åįķçĭ¬
    0.08
    èį¯
    0.08
    Activations Density 0.064%

    No Known Activations