© 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. 19238
    Prev
    Next
    INDEX
    Explanations

    numbers and letters forming codes, addresses, or specific identifiers

    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
    æĮ£
    -0.09
    åIJĮç±»
    -0.09
    è²´
    -0.09
    æŁĦ
    -0.09
    åĪĨ级
    -0.09
    è´µ
    -0.08
    hausen
    -0.08
    çħ²
    -0.08
    çłĶ究ä¸Ńå¿ĥ
    -0.08
    æĹłåħ³
    -0.08
    POSITIVE LOGITS
    山谷
    0.09
    ä¾Ŀ次
    0.09
    严峻
    0.09
    ÐŀС
    0.08
    çĤ¹å¤ļ
    0.08
    主èIJ¥ä¸ļåĬ¡
    0.08
    çªĴ
    0.08
    æģķ
    0.08
    _bug
    0.08
    ialog
    0.08
    Activations Density 0.210%

    No Known Activations