© 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. 1714
    Prev
    Next
    INDEX
    Explanations

    exactly what

    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»ħä¾ĽåıĤèĢĥ
    -0.10
    ä¸Ģå®ļ
    -0.10
    ä¸Ģå®ļæĺ¯
    -0.09
    å¦Ĥæŀľæĺ¯
    -0.09
    æł¹æľ¬æ²¡æľī
    -0.09
    åĹŁ
    -0.09
    ä»ħä»ħæĺ¯
    -0.09
    æ¯ķç«Łæĺ¯
    -0.08
    vue
    -0.08
    尤为
    -0.08
    POSITIVE LOGITS
    alls
    0.10
    æĿľç»Ŀ
    0.09
    å¼Ģå¹ķ
    0.09
    WithDuration
    0.09
    éľĨ
    0.09
    å®ŀçī©
    0.09
    ForObject
    0.09
    itude
    0.09
    åľºåIJĪ
    0.09
    åī
    0.09
    Activations Density 0.055%

    No Known Activations