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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34779
    Prev
    Next
    INDEX
    Explanations

    thrombosis and embolization

    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
    åIJī祥
    -0.10
    bak
    -0.09
     Ske
    -0.09
    è·ĭ
    -0.09
    å³°åĢ¼
    -0.09
    ÖĦ
    -0.09
    åĩłæŃ¥
    -0.08
    åľ°ä¸ĭ
    -0.08
    两åı¥
    -0.08
    éĢĦ
    -0.08
    POSITIVE LOGITS
    ä¸Ģæŀļ
    0.09
    ç¿Ĭ
    0.09
    åĮĿ
    0.09
    hood
    0.09
    ãĥĪãĥ©
    0.08
    éĺ»æŃ¢
    0.08
    Translate
    0.08
    Continue
    0.08
    egan
    0.08
    .localized
    0.08
    Activations Density 0.212%

    No Known Activations