© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8179
    Prev
    Next
    INDEX
    Explanations

    floor or flooring

    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
    éĥ¦
    -0.09
    åĨĴ
    -0.09
    æĮĩ导
    -0.09
     Dice
    -0.08
    éŀį
    -0.08
    çļĦä¸ĢéĿ¢
    -0.08
    ðŁijī
    -0.08
    anja
    -0.08
    顺
    -0.08
    éģ®
    -0.08
    POSITIVE LOGITS
    è·º
    0.13
    éŀĭåŃIJ
    0.13
    éŀĭ
    0.13
    踢
    0.13
     shoes
    0.11
    踩
    0.11
    æľ¨åľ°æĿ¿
    0.10
    å¿łè¯ļ
    0.10
    åľ°æĿ¿
    0.10
     shoe
    0.10
    Activations Density 0.060%

    No Known Activations