© 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. 39299
    Prev
    Next
    INDEX
    Explanations

    awards and citations

    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
    èĺ§
    -0.09
    çŃ®
    -0.09
    (UINT
    -0.09
    å¼Ģ
    -0.09
     fim
    -0.08
    ôi
    -0.08
    ÑıÑģÑĮ
    -0.08
    æł·æĿ¿
    -0.08
    åĪ¨
    -0.08
    Disallow
    -0.08
    POSITIVE LOGITS
    ä¸Ģæŀļ
    0.14
    åħīèį£
    0.12
    绶
    0.12
    åĭĭç«ł
    0.10
    佩
    0.10
    åį°
    0.10
    ä¸Ĭå²Ĺ
    0.10
    缸åºĶçļĦ
    0.10
    æĺ¯çľŁçļĦ
    0.10
    å¢ŀæ·»
    0.10
    Activations Density 0.050%

    No Known Activations