© 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. 52118
    Prev
    Next
    INDEX
    Explanations

    failures, errors, mistakes, risks, fail

    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
    çĵ¶
    -0.10
    ç«ŀäºīåĬĽ
    -0.09
    ä¼Ĺ
    -0.09
    bell
    -0.09
    æĢ«
    -0.09
    âĸIJ
    -0.09
    è¾ĪåŃIJ
    -0.09
    éĤ¸
    -0.09
    æļ´
    -0.08
    .FETCH
    -0.08
    POSITIVE LOGITS
    失败
    0.16
    失误
    0.15
     failure
    0.12
    è·Į
    0.11
     mistakes
    0.11
    à¸ŀลาà¸Ķ
    0.11
    ä¸įæĢķ
    0.11
    çĬ¯
    0.11
    Fail
    0.10
    fall
    0.10
    Activations Density 0.069%

    No Known Activations