© 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. 38305
    Prev
    Next
    INDEX
    Explanations

    sweetheart would

    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
    pray
    -0.12
    ential
    -0.11
    manage
    -0.09
    éļĻ
    -0.09
    osti
    -0.08
    åij»
    -0.08
    mdb
    -0.08
    çļĦä¸ĢåĪĩ
    -0.08
    tant
    -0.08
    boat
    -0.08
    POSITIVE LOGITS
    ampo
    0.09
    æĬķèµĦé¢Ŀ
    0.08
    éļ¨æĻĤ
    0.08
    UnderTest
    0.08
    clubs
    0.08
    å¦ŀ
    0.08
    çļĦæĸĩåŃĹ
    0.08
    Ñİ
    0.08
    squ
    0.08
    ibs
    0.08
    Activations Density 0.002%

    No Known Activations