© 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. 24266
    Prev
    Next
    INDEX
    Explanations

    traditional

    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
    een
    -0.11
    -eyed
    -0.10
    俾
    -0.09
    ound
    -0.09
    ments
    -0.09
    ÑģÑı
    -0.09
    ousse
    -0.08
    itting
    -0.08
    éĩįè¦ģåİŁåĽł
    -0.08
    iden
    -0.08
    POSITIVE LOGITS
    ãģĤãĤĬãģ¾ãģĻãģĮ
    0.10
    lor
    0.10
    ional
    0.10
    ivic
    0.10
    æĢ§
    0.09
    ively
    0.09
    nal
    0.09
     xuyên
    0.09
    åģļæ³ķ
    0.09
    nelle
    0.09
    Activations Density 0.040%

    No Known Activations