© 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. 59441
    Prev
    Next
    INDEX
    Explanations

    biblical names and surnames

    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
    avo
    -0.10
    çĸ
    -0.09
     quo
    -0.09
    å¥ĩèij©
    -0.08
    ering
    -0.08
    yı
    -0.08
    è´ª
    -0.08
    ByUrl
    -0.08
    ue
    -0.08
     nou
    -0.08
    POSITIVE LOGITS
    æŦ
    0.10
    亶
    0.10
    son
    0.10
    é£İä¿Ĺ
    0.10
    sson
    0.10
    èŁł
    0.09
    åĭ¤
    0.09
    媳
    0.09
    LECT
    0.09
    å¾ķ
    0.09
    Activations Density 0.078%

    No Known Activations