© 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. 32437
    Prev
    Next
    INDEX
    Explanations

    disease course progression

    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
    æijĨåľ¨
    -0.10
    ä¸ĢæĿ¯
    -0.09
     ex
    -0.09
    对æѤ
    -0.08
    åħ¬çĶ¨
    -0.08
    åĨįä¸Ģ次
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
    é©Ń
    -0.08
    inki
    -0.08
    天åłĤ
    -0.08
    POSITIVE LOGITS
     progression
    0.12
    åıijå±ķè¶ĭåĬ¿
    0.10
    è¿Ľç¨ĭ
    0.10
    æ¼Ķåıĺ
    0.10
    åıijä½ľ
    0.09
    嶷
    0.09
    å³»
    0.09
    severity
    0.09
    åĢĻ
    0.09
    è¿Ľå±ķæĥħåĨµ
    0.09
    Activations Density 0.463%

    No Known Activations