© 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. 60659
    Prev
    Next
    INDEX
    Explanations

    point out / point me to

    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
    ëį°
    -0.10
    裳
    -0.10
    odash
    -0.10
    ording
    -0.09
    æĺ¯çľŁçļĦ
    -0.08
    æłĹ
    -0.08
    主è¦ģåĨħ容
    -0.08
    ×Ļ×ķ
    -0.08
    æĦıè§ģåıįé¦Ī
    -0.08
    ำ
    -0.08
    POSITIVE LOGITS
    åĩºäºĨ
    0.10
    åĩłä¸ª
    0.10
    渡
    0.09
    æĭ¨
    0.09
    kest
    0.09
    eler
    0.09
    åĪ°ä½į
    0.09
    -eyed
    0.08
    ican
    0.08
    ering
    0.08
    Activations Density 0.016%

    No Known Activations