© 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. 9574
    Prev
    Next
    INDEX
    Explanations

    ugly, bland, dull, boring descriptions

    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
    强çĥĪ
    -0.10
    æĪı
    -0.10
    举
    -0.10
    æĤł
    -0.09
    èĪī
    -0.09
    çĥ½
    -0.08
    ç¼ĵ
    -0.08
    宽æĿ¾
    -0.08
    å¹Į
    -0.08
     fit
    -0.08
    POSITIVE LOGITS
    ä¸ij
    0.16
    黯
    0.14
     dull
    0.14
    平淡
    0.13
    åįķè°ĥ
    0.13
    æŀ¯çĩ¥
    0.12
     ugly
    0.12
     bland
    0.12
    éĴĿ
    0.12
    庸
    0.11
    Activations Density 0.078%

    No Known Activations