© 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. 16657
    Prev
    Next
    INDEX
    Explanations

    how much

    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
    upid
    -0.10
    unist
    -0.10
    缸å½ĵ
    -0.10
    ä¸įè¿ľ
    -0.09
    æľ¬èº«å°±
    -0.09
    bst
    -0.09
    entlich
    -0.09
    æĽ´å¤ļ
    -0.08
    lod
    -0.08
    ÙģÙĪر
    -0.08
    POSITIVE LOGITS
    åıĹåĪ°äºĨ
    0.09
    éĩįè§Ĩ
    0.09
    马åĬĽ
    0.09
    éĿłè¿ij
    0.09
    ä¾ĿéĿł
    0.08
    .fac
    0.08
    ä»ĵ
    0.08
    æ²īæµ¸åľ¨
    0.08
    以人æ°ij
    0.08
    åīĬå¼±
    0.08
    Activations Density 0.041%

    No Known Activations