© 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. 10628
    Prev
    Next
    INDEX
    Explanations

    viewpoints and overlooks

    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
    èĨı
    -0.10
    éĻIJå®ļ
    -0.09
    åĮħåĽ´
    -0.09
    åħĭåĪ¶
    -0.08
    æ¼ı
    -0.08
    جار
    -0.08
    ä¸ĢæĶ¯
    -0.08
    ål
    -0.08
     жид
    -0.08
    仵
    -0.08
    POSITIVE LOGITS
    çŀŃ
    0.15
    çľº
    0.11
    çŀ°
    0.10
    è§Ī
    0.09
    æĶĢçĻ»
    0.09
    æĻĤãģ«ãģ¯
    0.09
    å¤ĦåĪĨ
    0.09
    é«ĺ空
    0.09
     observation
    0.09
    å±ķæľĽ
    0.09
    Activations Density 0.036%

    No Known Activations