© 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. 38673
    Prev
    Next
    INDEX
    Explanations

    links containing github.com or .com

    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
    ray
    -0.09
    å¿Ļ
    -0.08
     Starter
    -0.08
    å¾ģéĽĨ
    -0.08
    Base
    -0.08
    俳
    -0.08
    éĢĹ
    -0.08
    èĸ°
    -0.08
    å¤ĩ
    -0.07
    BAL
    -0.07
    POSITIVE LOGITS
    åīįè¿Ľ
    0.10
    æ»´æ»´
    0.10
    身为
    0.10
    è¿ĻæĶ¯
    0.10
    çijĽ
    0.10
    èħ®
    0.09
    æ²Ľ
    0.09
    éĺŁä¼į建设
    0.09
    è¯ľ
    0.09
     ENTITY
    0.09
    Activations Density 0.066%

    No Known Activations