© 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. 56220
    Prev
    Next
    INDEX
    Explanations

    timing and durations

    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
     Ñģоб
    -0.10
    -lat
    -0.09
    _LAT
    -0.09
     пÑģ
    -0.09
    åĵī
    -0.09
    çľŁäºº
    -0.09
    åīįæĻ¯
    -0.09
    .getError
    -0.09
    inium
    -0.09
    æĢ»éĥ¨
    -0.09
    POSITIVE LOGITS
    æĬ½å¥ĸ
    0.09
    ä»ħä»ħ
    0.09
    æľŁéĹ´
    0.09
    帷
    0.09
    äºĨåįĬ天
    0.09
    ä¸Ģ缴åĪ°
    0.09
    ä¸ºæľŁ
    0.08
    èĥŀ
    0.08
    缴åĪ°
    0.08
    éĢĭ
    0.08
    Activations Density 0.191%

    No Known Activations