© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20255
    Prev
    Next
    INDEX
    Explanations

    general,

    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
    çļĦéĥ¨åĪĨ
    -0.11
    UTION
    -0.09
    ç³Ł
    -0.09
    éĿ´
    -0.09
    åı¦è¡Į
    -0.09
     kısı
    -0.09
    æijĦå½±å¸Ī
    -0.09
    åı¨
    -0.09
    indle
    -0.09
    个å°ı
    -0.08
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.11
     xuyên
    0.11
    æĿ¥è¯´
    0.10
     speaking
    0.10
    ä¾Ĩ說
    0.10
    èĢĮè¨Ģ
    0.09
    äºīåıĸ
    0.08
    æĿ¥çľĭ
    0.08
    åºĶ
    0.08
    åıªæľīä¸Ģ个
    0.08
    Activations Density 0.068%

    No Known Activations