© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37523
    Prev
    Next
    INDEX
    Explanations

    if they

    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
    7
    -0.09
    3
    -0.08
    为æĤ¨
    -0.08
    6
    -0.08
    4
    -0.08
    9
    -0.08
    8
    -0.08
    为äºĨéģ¿åħį
    -0.08
    为äºĨ
    -0.08
    5
    -0.08
    POSITIVE LOGITS
    è®¤çľŁåŃ¦ä¹ł
    0.16
    好好
    0.15
    proper
    0.15
     пÑĢавилÑĮно
    0.14
     properly
    0.14
    è®¤çľŁèIJ½å®ŀ
    0.14
     proper
    0.13
    æŃ£ç¡®
    0.13
    åıªè¦ģ
    0.13
    åħ±åIJĮåĬªåĬĽ
    0.13
    Activations Density 0.054%

    No Known Activations