© 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. 62993
    Prev
    Next
    INDEX
    Explanations

    small and medium businesses

    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
    åŁĭ
    -0.10
    ILA
    -0.09
    adm
    -0.08
    声
    -0.08
    ici
    -0.08
    ispers
    -0.08
    åIJIJ
    -0.08
    让大家
    -0.08
    Lux
    -0.08
    éĢļ讯
    -0.08
    POSITIVE LOGITS
    å°ıå¾®ä¼ģä¸ļ
    0.21
    ä¸Ńå°ıä¼ģä¸ļ
    0.19
    å°ıå¾®
    0.16
    ä¸Ńå°ı
    0.15
     Small
    0.14
     SME
    0.13
     small
    0.12
     мал
    0.12
    Small
    0.12
    ä¸Ńå°ıåŀĭ
    0.12
    Activations Density 0.104%

    No Known Activations