© 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. 51574
    Prev
    Next
    INDEX
    Explanations

    tendon injuries and disorders

    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
    以åħį
    -0.10
    çł
    -0.09
    ¤
    -0.09
    èĺħ
    -0.09
    äºĨä¸Ģä¸ĭ
    -0.09
    lez
    -0.09
    éĢ¸
    -0.09
    åŁ¯
    -0.09
    avings
    -0.08
    è¿ĩçļĦ
    -0.08
    POSITIVE LOGITS
    stry
    0.12
    Thor
    0.10
    lac
    0.09
    strain
    0.09
    STRU
    0.09
    çĤİ
    0.09
    sWith
    0.09
    дÑĥ
    0.08
    åľ¨åĮĹ京
    0.08
    æĸĩ书
    0.08
    Activations Density 0.022%

    No Known Activations