© 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. 29524
    Prev
    Next
    INDEX
    Explanations

    learn more

    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
    iamond
    -0.10
    Ñĥн
    -0.09
    ATING
    -0.09
    ties
    -0.09
    ẩm
    -0.09
    æ¯ĵ
    -0.08
    ylon
    -0.08
    atem
    -0.08
    ols
    -0.08
    reed
    -0.08
    POSITIVE LOGITS
     rằng
    0.12
    arie
    0.09
    fulness
    0.09
    coholic
    0.09
    ä»Ģä¹Īåı«
    0.08
    ä¸įéĶĻçļĦ
    0.08
    使çĶ¨æĿĥ
    0.08
    æİĸ
    0.08
    ells
    0.08
    ikel
    0.08
    Activations Density 0.031%

    No Known Activations