© 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. 63259
    Prev
    Next
    INDEX
    Explanations

    modals followed by be or have

    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
    cher
    -0.09
    EIF
    -0.09
    говоÑĢ
    -0.09
    æªĢ
    -0.08
    IAM
    -0.08
    èĩ³æĸ¼
    -0.08
    对èĩªå·±çļĦ
    -0.08
    åħ¶ä»ĸçļĦ
    -0.08
    ç«ĭãģ¡
    -0.08
    çIJ´
    -0.08
    POSITIVE LOGITS
    使å¾Ĺ
    0.10
    èĩĬ
    0.10
    æģķ
    0.09
    èĪģ
    0.09
    å´½
    0.09
    æĹħ游èµĦæºIJ
    0.08
    åıįèħIJåĢ¡å»ī
    0.08
    ä¿ĥ使
    0.08
    ä¼ļå±ķä¸Ńå¿ĥ
    0.08
    åļĵ
    0.08
    Activations Density 0.981%

    No Known Activations