© 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. 11074
    Prev
    Next
    INDEX
    Explanations

    biographies and memoirs

    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
    ible
    -0.10
    mask
    -0.08
    è¯įæ±ĩ
    -0.08
     Thomson
    -0.08
    好çļĦ
    -0.08
    款项
    -0.08
    anne
    -0.08
    论述
    -0.08
    寥
    -0.08
     Ple
    -0.07
    POSITIVE LOGITS
    shelf
    0.11
    eton
    0.11
    sWith
    0.10
    -ish
    0.10
    æĬ¥ä¸ļ
    0.10
    acles
    0.10
    çīĿ
    0.10
    åĩłåįģå¹´
    0.10
    åĽŀå¿Ĩ
    0.09
    èĥ¼
    0.09
    Activations Density 0.011%

    No Known Activations