© 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. 18694
    Prev
    Next
    INDEX
    Explanations

    infant vision and development

    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
    åijĬè¯ī大家
    -0.11
    å¿ĥåºķ
    -0.09
    女åŃIJ
    -0.09
    女æĢ§
    -0.09
    å¿ĥçģµ
    -0.09
    èľĤ
    -0.09
    æľªæĪIJå¹´
    -0.09
    ä¸Ģç¬Ķ
    -0.09
    å¦ĩ
    -0.09
    çĶ·æĢ§
    -0.09
    POSITIVE LOGITS
    åĽ´
    0.10
    å®Ŀå®Ŀ
    0.09
     diaper
    0.09
    åĴ¿
    0.09
    caught
    0.09
    EC
    0.09
    åĩºçĶŁ
    0.09
    è·
    0.09
    翻身
    0.09
    Baby
    0.08
    Activations Density 0.220%

    No Known Activations