© 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. 61863
    Prev
    Next
    INDEX
    Explanations

    previews, encyclopedia, hemostasis, armed

    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
    udad
    -0.10
    æĮĸæİĺ
    -0.10
    æŃ£å¼ı
    -0.09
    bjerg
    -0.09
    ict
    -0.09
    æī¿æĭħ责任
    -0.09
    æݥ管
    -0.09
    eree
    -0.08
    æĮ¤
    -0.08
    assel
    -0.08
    POSITIVE LOGITS
    æĨĭ
    0.09
    æ´»å¾Ĺ
    0.08
    виÑģ
    0.08
    ibo
    0.08
    åİĦ
    0.08
    .Observer
    0.08
    å¥ijæľº
    0.08
    Ended
    0.08
    çĶ²çĬ¶
    0.08
     Tyson
    0.07
    Activations Density 0.005%

    No Known Activations