© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53199
    Prev
    Next
    INDEX
    Explanations

    maternal and neonatal tetanus

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ç´į
    -0.09
    éĢ¸
    -0.08
     tract
    -0.08
    åħħ
    -0.08
    ç²ī
    -0.08
     plat
    -0.08
     subt
    -0.08
     extr
    -0.08
    ç¢İ
    -0.08
    èĩªæĿĢ
    -0.08
    POSITIVE LOGITS
    åģļçļĦäºĭæĥħ
    0.11
    æİ¥ç§į
    0.10
    çĹĺ
    0.10
    åľŁè±ª
    0.10
     measles
    0.09
    æĥ°
    0.09
    欢è¿İæĤ¨
    0.09
     зÑĥб
    0.09
    artin
    0.09
    çİ©åħ·
    0.09
    Activations Density 0.070%

    No Known Activations