© 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. 8856
    Prev
    Next
    INDEX
    Explanations

    personal experiences and observations

    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
    åı¬
    -0.09
    享åıĹ
    -0.08
    å¹ħ
    -0.08
    享
    -0.08
    å¾ĹçĽĬ
    -0.08
    åıij声
    -0.08
    ä¸įæľį
    -0.08
    éĻĪè¿°
    -0.08
    é¢ĺ主
    -0.08
    èĩªçIJĨ
    -0.08
    POSITIVE LOGITS
    æİ¥æīĭ
    0.16
    åıĹçIJĨ
    0.13
    客æĪ·çļĦ
    0.13
    帮
    0.13
    clients
    0.12
    误导
    0.11
    åĬĿ
    0.11
     clients
    0.11
    为客æĪ·
    0.11
    帮åĬ©
    0.11
    Activations Density 0.202%

    No Known Activations