© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8474
    Prev
    Next
    INDEX
    Explanations

    emotions and states of mind

    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
    çŀİ
    -0.11
    缩水
    -0.10
    èĻı
    -0.10
    绣çŃ¹æİ¨è¿Ľ
    -0.10
    FFFFFFFF
    -0.10
    躬
    -0.10
    åŃ
    -0.09
    æĺ¯å¤ļä¹Ī
    -0.09
    æģ¶éŃĶ
    -0.09
    аниз
    -0.09
    POSITIVE LOGITS
    åľ°çľĭçĿĢ
    0.13
    çļĦçľ¼ç¥ŀ
    0.10
    rm
    0.10
    åľ°è¯´
    0.10
    -looking
    0.09
     rm
    0.09
    åľ°
    0.09
    ç¥ŀæĥħ
    0.09
    çľĭçĿĢ
    0.08
     Stroke
    0.08
    Activations Density 0.057%

    No Known Activations