© 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. 48764
    Prev
    Next
    INDEX
    Explanations

    source code redistribution

    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
    åľ¨è¿Ļç§į
    -0.13
    åľ¨åĨħçļĦ
    -0.13
    åľ¨å®¶
    -0.12
    ä½łåľ¨
    -0.11
    åľ¨ä¸Ģ个
    -0.11
     ÙģÙĬ
    -0.11
    ä½ıåľ¨
    -0.10
    å¥¹åľ¨
    -0.10
    åľ¨è¿Ļ
    -0.10
    åľ¨åºĬä¸Ĭ
    -0.10
    POSITIVE LOGITS
     guise
    0.14
     nutshell
    0.12
     midst
    0.12
     ×ķ×ij
    0.12
     context
    0.11
    çļĦ帮åĬ©ä¸ĭ
    0.11
     manner
    0.11
    人群ä¸Ń
    0.11
     contexts
    0.11
     vicinity
    0.10
    Activations Density 3.295%

    No Known Activations