© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56888
    Prev
    Next
    INDEX
    Explanations

    placental and prenatal care

    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
     pencils
    -0.09
    bon
    -0.09
     Claw
    -0.08
     bon
    -0.08
    bib
    -0.08
    ä¸ľæµ·
    -0.08
     himself
    -0.08
    loth
    -0.08
    çŃ¹
    -0.08
    6
    -0.08
    POSITIVE LOGITS
    产å¦ĩ
    0.13
    她们
    0.12
    æĦī
    0.11
    éģģ
    0.11
    éĢģè¾¾
    0.10
    鸨
    0.10
    å¦ĩ
    0.10
    å¾ĩ
    0.10
    é«ĺæ½®
    0.09
    å§Ķ
    0.09
    Activations Density 0.225%

    No Known Activations