© 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. 11666
    Prev
    Next
    INDEX
    Explanations

    chromosomal, chromophore, chromite

    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
    ugas
    -0.10
    ement
    -0.09
    otch
    -0.09
    æĹİ
    -0.09
    tings
    -0.09
     اÙĦØ£Ùħر
    -0.08
    atory
    -0.08
    eners
    -0.08
    PathComponent
    -0.08
    ities
    -0.08
    POSITIVE LOGITS
    亮丽
    0.10
    myp
    0.09
    çĶŁäº§æĢ»åĢ¼
    0.09
    ãģĭãģ£ãģŁ
    0.09
     Vale
    0.09
    arges
    0.09
    人èĦ¸
    0.08
    åľ¨çĶŁæ´»ä¸Ń
    0.08
    -coded
    0.08
    ester
    0.08
    Activations Density 0.068%

    No Known Activations