© 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. 62981
    Prev
    Next
    INDEX
    Explanations

    too much or too extreme

    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
    çIJ¥
    -0.10
    -gnu
    -0.10
    å¾Īéĩįè¦ģçļĦ
    -0.10
    æİīäºĨ
    -0.10
    éĦ¢
    -0.09
    quate
    -0.09
    æijĪ
    -0.09
    å¾Īé«ĺçļĦ
    -0.09
    nt
    -0.08
    å¾Ī大çļĦ
    -0.08
    POSITIVE LOGITS
    人éĹ´
    0.10
    ean
    0.09
     TOO
    0.08
    æĮīä¸ĭ
    0.08
    eshire
    0.08
    æĮ¥æīĭ
    0.08
    æĪIJçĨŁ
    0.08
    容æĺĵ
    0.08
    acd
    0.08
    bild
    0.08
    Activations Density 0.004%

    No Known Activations