© 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. 18536
    Prev
    Next
    INDEX
    Explanations

    born in

    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
    ä¸ĩæĪ·
    -0.10
     sanctioned
    -0.09
    缸è§ģ
    -0.08
    ses
    -0.08
    æĿij级
    -0.08
    åħ³èģĶ
    -0.08
    ä¸ĢéĿ¢
    -0.08
    ç¥
    -0.08
    å¹³æŶ
    -0.08
    à¸Ļาม
    -0.08
    POSITIVE LOGITS
    åĩºçĶŁ
    0.15
    born
    0.14
    -born
    0.14
    çĶŁãģ¾ãĤĮ
    0.13
    åĩºçĶŁäºİ
    0.12
     born
    0.11
     Born
    0.11
    æ¯ķä¸ļäºİ
    0.10
    çĶŁäºİ
    0.10
    åĥŃ
    0.10
    Activations Density 0.090%

    No Known Activations