© 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. 62190
    Prev
    Next
    INDEX
    Explanations

    take, forgotten, want, ate, sees, selected, feel

    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
    æĥ³åĥı
    -0.09
     ngữ
    -0.09
    说æĪij
    -0.09
    ray
    -0.09
    éģı
    -0.08
    èĿ¶
    -0.08
     Fleming
    -0.08
    raf
    -0.08
    åīĸ
    -0.08
     Veg
    -0.08
    POSITIVE LOGITS
    ç¬ĶèĢħ
    0.13
    åºĶæľīçļĦ
    0.12
    ä¹ŁåºĶ该
    0.10
    åºĶå½ĵ
    0.10
    äºĨåIJ§
    0.09
    opal
    0.09
    鸾
    0.09
    æĩī該
    0.09
    åºĶ该
    0.09
    ä¸į妨
    0.09
    Activations Density 0.341%

    No Known Activations