© 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. 38280
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by context

    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
    è¿Ļæł·åģļ
    -0.09
    cz
    -0.08
    å®ĺ
    -0.08
    plier
    -0.08
    0
    -0.08
    spread
    -0.07
    è¿Ļä¹Īåģļ
    -0.07
    好åĩłä¸ª
    -0.07
    æīĢåľ¨çļĦ
    -0.07
    å¥
    -0.07
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.12
    çĶŁæķĪ
    0.10
    æĪĸèĢħåħ¶ä»ĸ
    0.10
    æĦį
    0.10
     Territories
    0.09
    istes
    0.09
    æīĢè¬Ĥ
    0.09
    æīĢè°ĵ
    0.09
    çļĦ帮åĬ©
    0.09
    éľĨ
    0.09
    Activations Density 0.098%

    No Known Activations