© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8323
    Prev
    Next
    INDEX
    Explanations

    penile structure or medical conditions

    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
    æĶĢ
    -0.09
    лÑİÑĩ
    -0.08
    æ¤İ
    -0.08
    赤
    -0.08
    aved
    -0.08
     amen
    -0.08
    纡
    -0.08
    å¸¦ä½ł
    -0.08
    头çĹĽ
    -0.08
    æĿ¥ç͵
    -0.08
    POSITIVE LOGITS
    履约
    0.11
    eland
    0.09
    çļĦä¸ĸçķĮ
    0.09
    æĮŁ
    0.09
     cas
    0.09
     Kling
    0.09
    zs
    0.08
    蹬
    0.08
    éĹ²
    0.08
    ivic
    0.08
    Activations Density 0.191%

    No Known Activations