© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21729
    Prev
    Next
    INDEX
    Explanations

    signs listing items or availabilities

    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
    å¹³æ°ij
    -0.11
    èĵį
    -0.09
     mute
    -0.09
    åĽĽä¸ªæĸ¹éĿ¢
    -0.09
    å§Ķ
    -0.09
    æ¹®
    -0.09
    çĤ¸å¼¹
    -0.08
    å½»
    -0.08
    ICollection
    -0.08
    SSERT
    -0.08
    POSITIVE LOGITS
    æŁIJæŁIJ
    0.11
    æŁIJ
    0.08
    æ¸į
    0.08
    åĭ¿
    0.08
    æĽ´å¤ļä¿¡æģ¯
    0.08
    举æĬ¥çĶµè¯Ŀ
    0.08
    åŃĹæł·
    0.08
    è¿Ļå°±æĺ¯
    0.08
    aml
    0.08
    è´¹
    0.08
    Activations Density 0.114%

    No Known Activations