© 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. 36809
    Prev
    Next
    INDEX
    Explanations

    historical and conceptual contexts

    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
    å¹²èĦĨ
    -0.09
    缮åīįæŃ£åľ¨
    -0.09
    å½ĵä»Ĭ
    -0.09
    rou
    -0.08
    çİ°ä»»
    -0.08
    æĭ¿æĿ¥
    -0.08
    çİ°è¡Į
    -0.08
    hyth
    -0.08
    寨
    -0.08
    å½ĵåīį
    -0.08
    POSITIVE LOGITS
    æľĢå¤ļ
    0.09
    é¦ĸä½į
    0.08
     gender
    0.08
    аÑĢÑĮ
    0.08
    ä¼ijéĹ²
    0.08
    å½ĵæŶ
    0.08
    æĢ§åĪ«
    0.08
    onian
    0.08
    early
    0.08
    éĢļä¿Ĺ
    0.08
    Activations Density 0.176%

    No Known Activations