© 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. 1817
    Prev
    Next
    INDEX
    Explanations

    sharing stories and testimonials

    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
    å°ıå¿ĥ翼翼
    -0.09
    çļĦåħ´è¶£
    -0.09
    èģļåIJĪ
    -0.08
    æŃī
    -0.08
    æŃ¤é¡¹
    -0.08
    æĹ¶æľŁçļĦ
    -0.08
    é¢ĦçķĻ
    -0.08
    å¹´ä¹ĭ
    -0.08
     Affero
    -0.08
    å¥Ī
    -0.08
    POSITIVE LOGITS
    æ¡Īä¾ĭ
    0.18
    åħ¸åŀĭ
    0.14
    åħ¸åŀĭæ¡Īä¾ĭ
    0.13
    æķħäºĭ
    0.13
    imonials
    0.13
    çĹħä¾ĭ
    0.13
     stories
    0.12
    æĦŁäºº
    0.12
     testimonials
    0.12
     Äijiá»ĥn
    0.12
    Activations Density 0.185%

    No Known Activations