© 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. 2233
    Prev
    Next
    INDEX
    Explanations

    riding at

    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
    äºĶåĽĽ
    -0.09
    寿
    -0.09
    顽强
    -0.08
    足
    -0.08
     Crowd
    -0.08
    æīĺ
    -0.08
    ä¸Ģ次æĢ§
    -0.08
    Inf
    -0.08
    iou
    -0.08
    _AUX
    -0.08
    POSITIVE LOGITS
    龸éģĵ
    0.10
    åīįä¸ĸ
    0.10
    客æ°Ķ
    0.10
    æ²ħ
    0.09
    ä¸ĸçķĮ第ä¸Ģ
    0.09
    æĿľç»Ŀ
    0.09
    éªĪ
    0.09
    ãĥĨãĥ³
    0.09
    å¼¼
    0.09
    èĭķ
    0.09
    Activations Density 0.202%

    No Known Activations