© 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. 8121
    Prev
    Next
    INDEX
    Explanations

    copyrighted works and legal terms

    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
     Overflow
    -0.09
    å¹³æŶ
    -0.08
    è¥Ł
    -0.08
    ä¸įå¿į
    -0.08
    æľīåħ³
    -0.08
    åħ¨å¤©
    -0.08
    dera
    -0.08
     caus
    -0.08
    æľīåħ³éĥ¨éŨ
    -0.08
    å³°ä¼ļ
    -0.08
    POSITIVE LOGITS
    çĭ¬
    0.14
    çį¨
    0.13
    对åħ¶
    0.09
     ÅĽwie
    0.09
     copyrighted
    0.09
    åī©ä¸ĭçļĦ
    0.09
    çķĮéĿ¢
    0.09
    åIJįå½ķ
    0.09
    èĦļ
    0.09
    аÑĤÑĥÑĢ
    0.09
    Activations Density 0.131%

    No Known Activations