© 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. 26309
    Prev
    Next
    INDEX
    Explanations

    immediately or directly

    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
    phant
    -0.13
    å¼Ĥåľ°
    -0.09
    éªĮ
    -0.09
    å¹¹
    -0.09
    å®ŀçī©
    -0.09
    ä»°
    -0.09
    foon
    -0.08
    ason
    -0.08
    æĦĪ
    -0.08
     Snap
    -0.08
    POSITIVE LOGITS
    æľĹ
    0.11
    ANTE
    0.10
    ante
    0.09
    éĥİ
    0.09
    尺度
    0.09
    rink
    0.08
    æĬĬè¿Ļ个
    0.08
    éħĴä¸ļ
    0.08
    еÑģÑĤи
    0.08
    urg
    0.08
    Activations Density 0.007%

    No Known Activations