© 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. 2666
    Prev
    Next
    INDEX
    Explanations

    fired, sacked, dismissed, canned

    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
    é¹
    -0.09
    ç´ł
    -0.09
    线ä¸ĭ
    -0.09
    è¡Ļ
    -0.09
     cess
    -0.09
    度è¿ĩ
    -0.09
    åįĵè¶Ĭ
    -0.09
    że
    -0.08
    enus
    -0.08
    å¢Ģ
    -0.08
    POSITIVE LOGITS
    åĩºå±Ģ
    0.10
    cant
    0.09
    æİī
    0.09
    æİīäºĨ
    0.09
    棹
    0.09
    æµij
    0.09
    Callbacks
    0.09
     khá»ıi
    0.09
    åİŁåĽłæĺ¯
    0.09
    念头
    0.08
    Activations Density 0.020%

    No Known Activations