© 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. 4306
    Prev
    Next
    INDEX
    Explanations

    file format converters

    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
    æĵ¦
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    dit
    -0.08
    ncy
    -0.08
    å·§
    -0.08
     incidental
    -0.08
    éĶ®çĽĺ
    -0.08
    TTY
    -0.08
    SURE
    -0.08
    å·²ä¹ħ
    -0.08
    POSITIVE LOGITS
    å°±è¶Ĭ
    0.10
    æĹłç¼Ŀ
    0.10
    _ready
    0.10
    带走
    0.09
    çļĦå½¢å¼ı
    0.09
    åĨ¤
    0.09
    \Application
    0.09
    ä¸ºçĽ®æłĩ
    0.09
    æĮģ
    0.09
    çŃīå½¢å¼ı
    0.09
    Activations Density 0.341%

    No Known Activations