© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38131
    Prev
    Next
    INDEX
    Explanations

    Sauvignon Blanc

    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
    红èī²
    -0.11
     red
    -0.11
    西红
    -0.10
    ä¸ļä½Ļ
    -0.09
    红
    -0.09
     lipstick
    -0.09
    çĦĸ
    -0.09
    _Red
    -0.09
    éĢłè¡Ģ
    -0.09
    opa
    -0.09
    POSITIVE LOGITS
     Whites
    0.10
    åŤ
    0.09
     اÙĦتج
    0.09
     flute
    0.09
     whites
    0.08
    å¾¹
    0.08
    ÙģÙĦ
    0.08
    folio
    0.08
     кли
    0.08
    .args
    0.08
    Activations Density 0.011%

    No Known Activations