© 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. 16940
    Prev
    Next
    INDEX
    Explanations

    hydrodynamics, hydraulics, hydrogen, hydrophobic

    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
    ult
    -0.10
    ä¸Ĭåīį
    -0.10
    aint
    -0.09
    ctors
    -0.08
    ulti
    -0.08
    illac
    -0.08
    baum
    -0.08
    é¢Ĩ
    -0.08
    èĩĨ
    -0.08
    GU
    -0.08
    POSITIVE LOGITS
    лиÑĩ
    0.11
    å¸ĪåħĦ
    0.10
    漪
    0.10
    çı¥
    0.09
    æ²½
    0.09
    å·¥ä½ľç«Ļ
    0.09
    çĸıéĢļ
    0.09
    çģĮæºī
    0.09
    å·¥ä½ľçļĦ
    0.09
    岸边
    0.09
    Activations Density 0.060%

    No Known Activations