© 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. 37529
    Prev
    Next
    INDEX
    Explanations

    Achilles and ACL injuries

    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
    ç³ł
    -0.10
    èµ·æĿ¥äºĨ
    -0.10
    æĪ·åı£
    -0.09
    ÑĭÑĪ
    -0.09
    å¿¿
    -0.09
    æıIJè´¨
    -0.09
    åIJĦ家
    -0.09
    æ²Į
    -0.09
    æľŁæľ«
    -0.08
    edi
    -0.08
    POSITIVE LOGITS
    à¹Į
    0.11
    åĨ¥
    0.09
    .Inv
    0.09
    èģªæĺİ
    0.09
    ipe
    0.08
     rex
    0.08
    çŃĭ
    0.08
    elson
    0.08
    çĨŁ
    0.08
    Dispatch
    0.08
    Activations Density 0.039%

    No Known Activations