© 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. 34346
    Prev
    Next
    INDEX
    Explanations

    reiterating or repeating

    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
    æľīæ¯Ĵ
    -0.10
    æ´»
    -0.09
    inton
    -0.09
    æĻºåºĵ
    -0.08
    æķĻä¼ļ
    -0.08
    зв
    -0.08
    ä¸ĢçĶŁ
    -0.08
    åIJ¬è¯´
    -0.08
    æľī趣çļĦ
    -0.08
    ðŁĵķ
    -0.08
    POSITIVE LOGITS
    éĩįå¤į
    0.12
    ä»»ä½ķæŶåĢĻ
    0.12
    åĨį次
    0.11
    强è°ĥ
    0.11
    éĩįæĸ°
    0.10
    è¿ĻéĩĮæĺ¯
    0.10
    天涯
    0.09
     reiterated
    0.09
    åĨį度
    0.09
    ä¸Ģéģį
    0.09
    Activations Density 0.056%

    No Known Activations