© 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. 38997
    Prev
    Next
    INDEX
    Explanations

    source of infection

    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
     extrad
    -0.10
    .prepare
    -0.09
    æĶ¾åģĩ
    -0.09
    ä¸Ľä¹¦
    -0.09
    å¥Ķè·ij
    -0.09
    éĩįä¸Ń
    -0.08
    æ²IJæµ´
    -0.08
     hamm
    -0.08
     Colomb
    -0.08
    æĿ¥æī¾
    -0.08
    POSITIVE LOGITS
    æݥ触
    0.13
    æĴŃ
    0.11
    åħ±äº«
    0.10
     sharing
    0.10
    _shared
    0.10
     shared
    0.09
     Sharing
    0.09
    sharing
    0.09
     contacto
    0.09
    ä¼łæĴŃ
    0.09
    Activations Density 0.129%

    No Known Activations