© 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. 59416
    Prev
    Next
    INDEX
    Explanations

    art gallery names

    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
    ement
    -0.12
    lessly
    -0.10
    ément
    -0.09
    imizer
    -0.09
    ements
    -0.09
    ality
    -0.09
    æł·çļĦ
    -0.09
    ç£Ĭ
    -0.08
    磮
    -0.08
    æ¤IJ
    -0.08
    POSITIVE LOGITS
    èĢģæĿ¿
    0.10
    strand
    0.10
    ANGO
    0.09
    åĨħçļĦ
    0.09
    çŃīéĥ¨éŨ
    0.09
    erge
    0.09
    éŨåı£
    0.09
     thr
    0.09
    enty
    0.09
    inson
    0.08
    Activations Density 0.006%

    No Known Activations