© 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. 62640
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    Lifetime
    -0.10
    对åŃ©åŃIJ
    -0.09
    chai
    -0.08
    æĭ¾
    -0.08
    lien
    -0.08
    åĿIJ
    -0.08
    辨
    -0.08
    äºī龸
    -0.08
    å°ıäºĭ
    -0.08
    æĿĥ
    -0.08
    POSITIVE LOGITS
    éļ¶å±ŀäºİ
    0.20
    éļ¶å±ŀ
    0.16
    æīĢå±ŀ
    0.12
    å±ŀäºİ
    0.11
    å±ŀ
    0.11
    çļĦä¸Ģéĥ¨åĪĨ
    0.11
    å½Ĵå±ŀäºİ
    0.11
     thuá»Ļc
    0.10
    official
    0.10
    屬æĸ¼
    0.10
    Activations Density 0.162%

    No Known Activations