© 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. 64111
    Prev
    Next
    INDEX
    Explanations

    hemoglobin

    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
    æijĬ
    -0.11
    æ´¾
    -0.10
    饮çĶ¨
    -0.09
    éħ·
    -0.09
    çĨ¨
    -0.09
    缩水
    -0.09
    ä»İ严治
    -0.09
    åıªæĥ³
    -0.09
    .bd
    -0.09
    æĭī
    -0.09
    POSITIVE LOGITS
    çī
    0.09
    ä¼łéĢĴ
    0.09
    夹
    0.08
    oglobin
    0.08
    èķĬ
    0.08
    .transport
    0.08
    andon
    0.08
     Guinness
    0.08
    nosis
    0.08
    nan
    0.08
    Activations Density 0.341%

    No Known Activations