© 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. 37597
    Prev
    Next
    INDEX
    Explanations

    yeast and baking products

    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
    åIJ»
    -0.09
    éĻĶ
    -0.09
    åĮ¿
    -0.09
     Bars
    -0.09
    rior
    -0.09
    .eng
    -0.09
    ä¸įå°½
    -0.09
    plier
    -0.09
    åĴĢ
    -0.09
    è¶Ĭ
    -0.09
    POSITIVE LOGITS
     baking
    0.10
     اÙĦØ£ÙĪÙĦÙī
    0.10
    çĥĺçĦĻ
    0.10
    çĦĻ
    0.09
    èµŀæī¬
    0.09
     Bake
    0.09
    å¡ijéĢł
    0.09
     ds
    0.09
    被èªī
    0.08
    管家
    0.08
    Activations Density 0.039%

    No Known Activations