© 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. 7503
    Prev
    Next
    INDEX
    Explanations

    tells the story

    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
    对该
    -0.08
    imas
    -0.08
     Murder
    -0.08
    æīĢæıIJä¾ĽçļĦ
    -0.08
    éĻĪåĪĹ
    -0.08
    æĶ¾è¿ĩ
    -0.07
     triple
    -0.07
    é¢Ĩä¼ļ
    -0.07
     Momentum
    -0.07
     Triple
    -0.07
    POSITIVE LOGITS
    讲述äºĨ
    0.13
    讲述
    0.13
    æķħäºĭ
    0.13
    çļĦæķħäºĭ
    0.12
    主人åħ¬
    0.11
    çĶ·ä¸»è§Ĵ
    0.10
    主è§Ĵ
    0.10
    çļĦæĥħ
    0.10
    ä¸Ģ群
    0.10
    åľ¨ä¸Ģ个
    0.10
    Activations Density 0.176%

    No Known Activations