© 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. 29811
    Prev
    Next
    INDEX
    Explanations

    possessives and common nouns

    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
    èĢģ人家
    -0.12
    çļĦä¸Ģ项
    -0.10
    æĺ¯ä¸Ģ款
    -0.10
    æĺ¯ä¸Ģä½į
    -0.09
    /or
    -0.09
    åı¦ä¸Ģä½į
    -0.09
    çļĦ年轻人
    -0.09
    ãĤĭãģ®ãģ¯
    -0.09
    鸾
    -0.09
    ä¸ĢäºĽ
    -0.09
    POSITIVE LOGITS
    ushi
    0.09
    arta
    0.09
    åĴĮåľ°åĮº
    0.08
    çĿ
    0.08
    ied
    0.08
    вед
    0.08
    线ä¸Ĭ线ä¸ĭ
    0.08
    iating
    0.08
    å¼ĢéĺĶ
    0.08
    iable
    0.08
    Activations Density 0.060%

    No Known Activations