© 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. 2098
    Prev
    Next
    INDEX
    Explanations

    recess

    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
    ç¯Ĩ
    -0.09
    ãģĦãģĨ
    -0.09
    端åįĪ
    -0.09
    ÙĪØ´
    -0.08
    æ¯ĵ
    -0.08
    åĵªä¸Ģ个
    -0.08
    çļĦå®ŀåĬĽ
    -0.08
    大家åĪĨ享
    -0.08
    -0.08
    Å¡t
    -0.08
    POSITIVE LOGITS
    loth
    0.10
    å¼Ģåı£
    0.10
    eper
    0.10
    æĸ°å¼Ģ
    0.09
    acro
    0.09
    emer
    0.09
    _codegen
    0.09
    ä¸įå½ĵ
    0.08
    åıī
    0.08
    umer
    0.08
    Activations Density 0.006%

    No Known Activations