© 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. 47938
    Prev
    Next
    INDEX
    Explanations

    name followed by 'is' or 'a'

    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
    ãģłãģ£ãģ¦
    -0.09
    çĽ´è¾¾
    -0.09
    缴è¾ĸ
    -0.08
    æĽ´åħ·
    -0.08
    icer
    -0.08
    çİĩè¾¾
    -0.08
    俦
    -0.08
    æĽ´æľī
    -0.08
    çľĭ书
    -0.08
    继ç»Ńä¿ĿæĮģ
    -0.08
    POSITIVE LOGITS
     presumably
    0.12
    æīĢè°ĵçļĦ
    0.12
    çļĦä¸Ģéĥ¨åĪĨ
    0.10
    éĢļ常
    0.09
    æīĢè°ĵ
    0.09
    æŁIJç§į
    0.09
    被称为
    0.09
     èĭ¥è¦ģ
    0.09
    æĺ¯ä»Ģä¹Īåij¢
    0.09
    è¿Ļ家åħ¬åı¸
    0.09
    Activations Density 0.666%

    No Known Activations