© 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. 53935
    Prev
    Next
    INDEX
    Explanations

    celebrities and famous people

    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
    ÐľÐŀ
    -0.09
    èĥĦ
    -0.09
    ä»İæѤ
    -0.09
    æ»ļæ»ļ
    -0.09
    åIJĮæľŁ
    -0.09
    åĴ±ä»¬
    -0.09
    éļĨ
    -0.09
    å£ģåŀĴ
    -0.08
    raith
    -0.08
    assage
    -0.08
    POSITIVE LOGITS
    åıijå±ķä¸Ń
    0.08
     Miche
    0.08
    棺
    0.08
    ä¸įçŁ¥ä¸į
    0.08
    éĤ¨
    0.08
    çĪĨ
    0.07
     Maid
    0.07
     أع
    0.07
     Boy
    0.07
     nc
    0.07
    Activations Density 0.323%

    No Known Activations