© 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. 38976
    Prev
    Next
    INDEX
    Explanations

    grumpy, bad-tempered, surly, tetchy, gruff

    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
    å±ķ
    -0.10
    oom
    -0.09
    æĶ¾å®½
    -0.09
    åıijåŀĭ
    -0.08
     pane
    -0.08
    robe
    -0.08
    èĦļ
    -0.08
    çĺĭ
    -0.08
    åīįçŀ»
    -0.08
    Ãłnh
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.12
    ingly
    0.10
    iest
    0.10
    ä¸Ī夫
    0.10
    ä¸įå·²
    0.09
    èĪ¬çļĦ
    0.09
    å¿ĥ缮
    0.09
    æµĴ
    0.09
    äºĨä¸Ģåı¥
    0.09
    ãģªãģĮãĤī
    0.09
    Activations Density 0.009%

    No Known Activations