© 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. 58842
    Prev
    Next
    INDEX
    Explanations

    food ingredients

    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
    osit
    -0.10
    äºī缸
    -0.09
    é©»
    -0.09
     surf
    -0.09
    åĩºåĽ½
    -0.08
    鸢
    -0.08
    é£İ鼨
    -0.08
    æŀ¯
    -0.08
    访è°Ī
    -0.08
    è±ķ
    -0.08
    POSITIVE LOGITS
    éĢĤéĩı
    0.10
    æijĬ
    0.10
    æIJģ
    0.10
    ernels
    0.09
    à¸ķะ
    0.09
    æĶ¾åħ¥
    0.09
    æŃ£å®Ĺ
    0.09
    好å¥ĩå¿ĥ
    0.09
    å¡ĺ
    0.09
    ãĥIJãĥ³
    0.09
    Activations Density 0.036%

    No Known Activations