© 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. 38819
    Prev
    Next
    INDEX
    Explanations

    instruments and techniques

    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
    åĺĺ
    -0.10
    ÙģÙĪ
    -0.10
    æĮŀ
    -0.09
    onta
    -0.09
    _MESH
    -0.09
    .ov
    -0.09
    å¼ĢåĬŀ
    -0.09
    uci
    -0.09
    å¼łå®¶çķĮ
    -0.08
    鸬
    -0.08
    POSITIVE LOGITS
    ãģĽãģĦ
    0.08
    ä¸įæĸŃæī©å¤§
    0.08
    ken
    0.08
    omy
    0.08
    oly
    0.08
     нем
    0.08
     ÑĢазнÑĭÑħ
    0.08
    åĻ¨
    0.08
    跨度
    0.08
    éĹ´
    0.07
    Activations Density 0.214%

    No Known Activations