© 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. 36220
    Prev
    Next
    INDEX
    Explanations

    syndrome, bevacizumab, license agreements

    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
    avr
    -0.09
    çľ¼åīį
    -0.09
    ä¸ĢåĪ»
    -0.08
    RAR
    -0.08
    èĬ³é¦Ļ
    -0.08
    ÑĤвоÑĢ
    -0.08
    éľĦ
    -0.08
    å«©
    -0.08
    åı¯æݧ
    -0.08
    rive
    -0.08
    POSITIVE LOGITS
    å®ļå¾ĭ
    0.11
    ç½ijå°ıç¼ĸ
    0.10
     Syndrome
    0.09
    ç½ij
    0.09
    éķľåŃIJ
    0.09
     syndrome
    0.09
    sembly
    0.09
    åįıä¼ļ
    0.09
    æĿ¡ä¾ĭ
    0.09
    æľ¯
    0.09
    Activations Density 0.528%

    No Known Activations