© 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. 4000
    Prev
    Next
    INDEX
    Explanations

    an followed by specific endings

    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
    rome
    -0.09
    ãĤ·ãĥ¼
    -0.09
    ÃŃst
    -0.09
    ä¸ĩåĪĨ
    -0.09
    _sta
    -0.09
    æľ¬ç«Ļ
    -0.09
    ãĤ¹ãĤ¿ãĥ³
    -0.08
    arians
    -0.08
    使åij½æĦŁ
    -0.08
    å±ģ
    -0.08
    POSITIVE LOGITS
    uck
    0.09
    æĬij
    0.09
    .Serializable
    0.09
    å·¡
    0.09
     Dustin
    0.09
     Tears
    0.09
    èĦĶ
    0.08
    ä¸į让
    0.08
     Sul
    0.08
    欧ç¾İ
    0.08
    Activations Density 0.022%

    No Known Activations