© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51032
    Prev
    Next
    INDEX
    Explanations

    collecting data

    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
    odor
    -0.11
    eed
    -0.10
    rame
    -0.09
    å¢Ļ
    -0.09
    润
    -0.09
    eer
    -0.09
     magn
    -0.08
    æĹ¶ç©º
    -0.08
    _GRA
    -0.08
     Magn
    -0.08
    POSITIVE LOGITS
    æĶ¶éĽĨ
    0.12
    æīĭ段
    0.10
    æIJľéĽĨ
    0.10
     Collect
    0.10
    è¶³å¤ŁçļĦ
    0.10
    ãĥıãĤ¦ãĤ¹
    0.10
    线ä¸ĭ
    0.09
     gather
    0.09
    Ñĩа
    0.09
    æĭľå¸Ī
    0.09
    Activations Density 0.115%

    No Known Activations