© 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. 8415
    Prev
    Next
    INDEX
    Explanations

    carpet, carpets, 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
    æ°´ä¸Ĭ
    -0.11
    emente
    -0.09
    ucha
    -0.09
    CRY
    -0.09
     Belly
    -0.09
    hecy
    -0.09
     Hond
    -0.08
     Johns
    -0.08
    å±Ī
    -0.08
     ÑĩÑĤ
    -0.08
    POSITIVE LOGITS
    åľ°æ¯¯
    0.16
     carpet
    0.14
     carpets
    0.12
     Carpet
    0.12
    毯
    0.11
    踢
    0.09
    æľºæ¢°åĮĸ
    0.09
    æ²Ļåıij
    0.09
    对æłĩ
    0.09
    æݥ纳
    0.09
    Activations Density 0.052%

    No Known Activations