© 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. 20876
    Prev
    Next
    INDEX
    Explanations

    glucuronide derivatives

    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
     fres
    -0.10
    igt
    -0.08
    ç½ijåıĭè¯Ħ论
    -0.08
    å¸ĪçĶŁ
    -0.08
    å½ĵå±Ģ
    -0.08
    伸
    -0.08
     bend
    -0.08
    elt
    -0.08
    äºīåĪĽ
    -0.08
    æ¯ģçģŃ
    -0.08
    POSITIVE LOGITS
    æĶ¶çº³
    0.11
    车åºĵ
    0.11
    纹
    0.10
    åİļéĩį
    0.09
    çĥŁèĬ±çĪĨ竹
    0.09
    é¦Ļåij³
    0.09
    æĴķ
    0.09
    éĽªèĬ±
    0.09
    æĸŃ
    0.09
    èĪ£
    0.09
    Activations Density 0.196%

    No Known Activations