© 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. 4827
    Prev
    Next
    INDEX
    Explanations

    shampoo, shower, bath, water

    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
    ìľ¤
    -0.10
    å°ıé¢Ŀ
    -0.09
    ç»°
    -0.09
    å¹´æľ«
    -0.09
    ä¸ŃæľŁ
    -0.09
    èµ·éĩįæľº
    -0.08
    æīŃ转
    -0.08
    æľĹ
    -0.08
    à¸ł
    -0.08
    åħ¬å¼Ģ
    -0.08
    POSITIVE LOGITS
     shampoo
    0.09
    èĬĹ
    0.09
    æĮģ
    0.09
    æ·ĭ
    0.08
     Survivor
    0.08
     Jad
    0.08
    chrom
    0.08
    ayo
    0.08
    ogi
    0.08
    çĶµä»·
    0.08
    Activations Density 0.063%

    No Known Activations