© 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. 48308
    Prev
    Next
    INDEX
    Explanations

    winning contest prize

    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
    ä¸Ģç»ı
    -0.10
    好çľĭçļĦ
    -0.10
    è¿ĺæĺ¯ä¼ļ
    -0.10
    çľĭçĤ¹
    -0.10
    è®®æ¡Ī
    -0.09
    ä¾Ľæ±Ĥ
    -0.09
    å·¥ä½ľä½ľé£İ
    -0.09
    ä¸įæ¸ħ
    -0.09
    好æĦŁ
    -0.09
    okie
    -0.08
    POSITIVE LOGITS
    ãĤ¢ãĤ¦
    0.09
    thy
    0.09
    mel
    0.08
    åij½ä¸Ń
    0.08
     mel
    0.08
    ÑĤел
    0.08
    xEE
    0.08
    _chance
    0.08
    人çĶŁçļĦ
    0.08
    доб
    0.08
    Activations Density 0.012%

    No Known Activations