© 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. 8349
    Prev
    Next
    INDEX
    Explanations

    In other words

    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
    istic
    -0.09
    åIJĦæľī
    -0.08
    åIJĦåįķä½į
    -0.08
    è¦ģä¹Ī
    -0.08
    tes
    -0.08
    éĵ¤
    -0.08
     RID
    -0.08
     Eck
    -0.08
    åľ¨åĨħçļĦ
    -0.08
    [((
    -0.08
    POSITIVE LOGITS
    ä¾Ĩ說
    0.11
    æĦıä¹īä¸Ĭ
    0.11
    æĿ¥è¯´
    0.10
    è¯Ŀ说
    0.10
    èĢĮè¨Ģ
    0.10
     же
    0.09
    æĹ¥æĻļéĹ´
    0.09
    ä¸Ģç«Ļ
    0.09
    说æĪij
    0.09
    icht
    0.09
    Activations Density 0.028%

    No Known Activations