© 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. 35319
    Prev
    Next
    INDEX
    Explanations

    days of the week

    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
    å¥Ĥ
    -0.10
    cala
    -0.10
    寡
    -0.09
    лÑİ
    -0.09
    ä¸Ģç¢Ĺ
    -0.09
    çĻ½éĽª
    -0.09
    诺è´Ŀå°Ķ
    -0.09
    éŨæĪ·
    -0.09
    èĩĤ
    -0.08
    æĦŁåıĹåĪ°äºĨ
    -0.08
    POSITIVE LOGITS
    æĺŁæľŁ
    0.10
     пÑıÑĤ
    0.10
    ë§Īëĭ¤
    0.10
    nesday
    0.10
    ä¸ĬåįĪ
    0.09
     Saturday
    0.09
    åij¼
    0.09
    æĹ¥åľ¨
    0.08
    eer
    0.08
    åij¨åħŃ
    0.08
    Activations Density 0.094%

    No Known Activations