© 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. 10926
    Prev
    Next
    INDEX
    Explanations

    hypertension management

    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
    ipur
    -0.11
    ç¿Ķ
    -0.10
    uel
    -0.09
    æĭ¼
    -0.09
    uele
    -0.09
    çIJĽ
    -0.09
    渣
    -0.09
    æīĵçĿĢ
    -0.09
    gart
    -0.09
    åı¯ä¿¡
    -0.09
    POSITIVE LOGITS
    éģ¿
    0.09
    éĴł
    0.08
    ldr
    0.08
    éģµ
    0.08
     Gew
    0.08
     journal
    0.08
    èĩªæ²»
    0.08
    æŁļ
    0.08
    桶
    0.08
    äºĪ
    0.08
    Activations Density 0.282%

    No Known Activations