© 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. 32943
    Prev
    Next
    INDEX
    Explanations

    as far as ... go

    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
    baugh
    -0.09
    /as
    -0.09
    ä¼ļ对
    -0.09
    åijĬè¯īæĪij们
    -0.09
    èı½
    -0.09
    IFI
    -0.09
    iffs
    -0.09
    嬷
    -0.09
    claimed
    -0.09
    人群ä¸Ń
    -0.09
    POSITIVE LOGITS
    çļĦè¯Ŀ
    0.10
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    0.09
    ahead
    0.09
    çļĦ話
    0.09
    åĩºè·¯
    0.09
    ä¿İ
    0.08
    ä¸ĭ鼨
    0.08
    ä»ĸæĺ¯ä¸Ģ个
    0.08
     Sle
    0.08
    PU
    0.08
    Activations Density 0.029%

    No Known Activations