© 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. 39296
    Prev
    Next
    INDEX
    Explanations

    of this type

    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
    ä¸į幸
    -0.09
     sorts
    -0.09
    驯
    -0.09
    aping
    -0.08
    ither
    -0.08
    鼾
    -0.08
    templ
    -0.08
     Hint
    -0.08
    æĪIJé¾Ļ
    -0.08
    æĿĤ
    -0.08
    POSITIVE LOGITS
    å¦ĤæѤ
    0.24
    è¿Ļä¹Ī
    0.23
    è¿Ļæł·çļĦ
    0.20
    è¿Ļæł·
    0.20
    è¿Ļä¹Ī大
    0.19
    è¿ĻèĪ¬
    0.19
    è¿Ļæł·ä¸Ģ个
    0.18
     ÑĤакого
    0.18
     such
    0.17
    éĢĻ麼
    0.17
    Activations Density 0.127%

    No Known Activations