© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37278
    Prev
    Next
    INDEX
    Explanations

    roll out

    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
    èĶļ
    -0.11
    çĴIJ
    -0.10
    éłĵ
    -0.10
    iland
    -0.10
    å¡ŀ
    -0.10
    dire
    -0.10
     sop
    -0.09
    éĤł
    -0.09
    éļĶçĿĢ
    -0.09
    Offline
    -0.09
    POSITIVE LOGITS
    åIJ
    0.10
    pagen
    0.09
    稽
    0.08
    è¶³å¤ŁçļĦ
    0.08
    èĩªçĦ¶èĢĮ
    0.08
    建æĪIJåIJİ
    0.08
    åįĥå¹´
    0.08
    åIJĪä¸Ģ
    0.08
    å®Įåħ¨æĺ¯
    0.08
     roll
    0.08
    Activations Density 0.006%

    No Known Activations