© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40138
    Prev
    Next
    INDEX
    Explanations

    ammonia or ammonium

    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
    Negative Logits
    å®ĥçļĦ
    -0.08
    itives
    -0.08
    æĬ¹
    -0.08
    沫
    -0.08
    ('*',
    -0.08
    anes
    -0.08
     Redistributions
    -0.08
    imdi
    -0.08
    åĨ·æ¼ł
    -0.08
    uur
    -0.08
    POSITIVE LOGITS
    åıŁ
    0.09
    aiser
    0.09
    ç¥IJ
    0.09
    æĹıèĩªæ²»åİ¿
    0.09
    æĪijæĬĬ
    0.08
    å¹²ä»Ģä¹Ī
    0.08
    çī¹äº§
    0.08
    autop
    0.08
    å·¥èīºåĵģ
    0.08
    éĢµ
    0.08
    Activations Density 0.014%

    No Known Activations