© 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. 30480
    Prev
    Next
    INDEX
    Explanations

    introduces an explanation

    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
    ITCH
    -0.10
    åĴĮå°ļ
    -0.10
    æľµ
    -0.09
    ìĸµ
    -0.09
    enor
    -0.09
     particulars
    -0.09
    sted
    -0.08
    CDF
    -0.08
    atz
    -0.08
    OUCH
    -0.08
    POSITIVE LOGITS
    ity
    0.09
    çļĦãģ«ãģ¯
    0.09
    eter
    0.09
     Warfare
    0.09
    tes
    0.09
    ÙĪا
    0.08
    å°±è¡Į
    0.08
    å°±æĺ¯ä¸Ģ个
    0.08
    缸å½ĵäºİ
    0.08
     zeroes
    0.08
    Activations Density 0.017%

    No Known Activations