© 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. 2596
    Prev
    Next
    INDEX
    Explanations

    presenting or speaking

    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
    æ²½
    -0.10
    éĶ£
    -0.10
    anner
    -0.09
    çIJ¦
    -0.09
    åıijå¸ĥçļĦ
    -0.09
    lish
    -0.09
    èİ·åĪ©
    -0.09
    erot
    -0.09
    åĶĩ
    -0.08
    æ··ä¹±
    -0.08
    POSITIVE LOGITS
     himself
    0.11
    以åħ¶
    0.10
    åĴĮä»ĸçļĦ
    0.10
    exus
    0.09
    为大家
    0.09
    дÑĢ
    0.09
    åľ¨ä»ĸçļĦ
    0.08
    ä»ĸçļĦ
    0.08
    为æĪij们
    0.08
    ç»Ļ大家
    0.08
    Activations Density 0.047%

    No Known Activations