© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19666
    Prev
    Next
    INDEX
    Explanations

    attempt and success

    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
    éļĻ
    -0.08
    FS
    -0.08
     FSM
    -0.08
    åºŁè¯Ŀ
    -0.08
    ä½Ĩ对äºİ
    -0.08
    çŁ¥è¯Ĩ
    -0.08
    .emit
    -0.08
    é¡·
    -0.07
    赶紧
    -0.07
    jar
    -0.07
    POSITIVE LOGITS
    æĪIJåĬŁ
    0.20
     succeed
    0.20
    æĪIJæķĪ
    0.20
     succeeded
    0.19
     succeeds
    0.18
    失败
    0.17
    åģļå¾Ĺ
    0.17
    æĪIJåĬŁçļĦ
    0.17
    æķĪæŀľ
    0.17
     berhasil
    0.16
    Activations Density 0.182%

    No Known Activations