© 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. 10356
    Prev
    Next
    INDEX
    Explanations

    university names

    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
    ammers
    -0.08
    å¸Ń
    -0.08
    åĵĪä½Ľ
    -0.08
    æİ¨è¿Ľ
    -0.08
    æĹ·
    -0.08
     Aspen
    -0.08
    åĪĴ
    -0.08
    éĥ¾
    -0.07
    orts
    -0.07
    åѦåłĤ
    -0.07
    POSITIVE LOGITS
    æĸ¡
    0.11
    çĮ¥
    0.10
    çļĦåķĨåĵģ
    0.09
    ä»»æķĻ
    0.09
    æķĸ
    0.09
    çĥ¹
    0.09
    å¼ĩ
    0.09
    geois
    0.09
    æªIJ
    0.09
    .ITEM
    0.08
    Activations Density 0.047%

    No Known Activations