© 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. 6435
    Prev
    Next
    INDEX
    Explanations

    urinary and urine related terms

    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
    æīĭä¸ŃçļĦ
    -0.11
    ëģĶ
    -0.11
    ness
    -0.11
    们çļĦ
    -0.09
     возд
    -0.09
    åħĪè¿ĽçļĦ
    -0.09
    èĩªèº«
    -0.09
    å¹½
    -0.09
    åĨħåľ°
    -0.09
    oft
    -0.08
    POSITIVE LOGITS
    åĪ¶åº¦æĶ¹éĿ©
    0.10
    asin
    0.09
    .createObject
    0.09
    agy
    0.09
    stein
    0.08
    пÑĢавлÑı
    0.08
     tract
    0.08
    _SEG
    0.08
    VERBOSE
    0.08
    ض
    0.08
    Activations Density 0.076%

    No Known Activations