© 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. 22112
    Prev
    Next
    INDEX
    Explanations

    lunar calendar and dates

    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
    èĮĥ
    -0.10
    é»ĺ
    -0.10
    rior
    -0.08
    楼ä¸ĭ
    -0.08
    沧
    -0.08
    åºŁçī©
    -0.08
    çIJĥåľº
    -0.08
    磻
    -0.08
    ì±ķ
    -0.08
    åĸĻ
    -0.08
    POSITIVE LOGITS
    åİ»çľĭçľĭ
    0.09
    åĨľåİĨ
    0.09
    éĢļè¡Įè¯ģ
    0.09
    糯米
    0.09
    æĶ¹éĿ©
    0.09
    éĢ¶
    0.09
    yll
    0.08
     calendar
    0.08
     Lith
    0.08
    欢
    0.08
    Activations Density 0.046%

    No Known Activations