© 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. 3794
    Prev
    Next
    INDEX
    Explanations

    vitamin and supplementation

    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
    lund
    -0.10
     обÑĥÑĩ
    -0.09
    åĽº
    -0.09
    oven
    -0.08
    èĬĬ
    -0.08
     pit
    -0.08
    ahi
    -0.08
    è¿·
    -0.08
     заÑĤ
    -0.08
    cing
    -0.08
    POSITIVE LOGITS
    ä¿Ŀåģ¥åĵģ
    0.15
    éļIJéļIJ
    0.10
    ç»´çĶŁç´ł
    0.10
     Schwe
    0.10
     vitamin
    0.10
    ãĤµãĥĹãĥª
    0.09
    è¯ģåĪ¸æĬķèµĦ
    0.09
     полÑĮз
    0.09
    çļĦæĹ¶ä»£
    0.09
    å®ļæľŁ
    0.09
    Activations Density 0.069%

    No Known Activations