© 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. 37850
    Prev
    Next
    INDEX
    Explanations

    ground or floor

    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
    们çļĦ
    -0.10
    天ä¸ĭ
    -0.10
    们
    -0.10
    ами
    -0.09
    eam
    -0.09
    们éĥ½
    -0.09
     reve
    -0.09
    èµĦ产è¯Ħä¼°
    -0.08
    ibur
    -0.08
    etri
    -0.08
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.10
    妥
    0.09
    ç®ĹäºĨ
    0.09
    umbo
    0.09
    oplay
    0.09
    å¬ī
    0.09
    辫
    0.09
    æ·±å¤Ħ
    0.08
    åįķè¯į
    0.08
    iffin
    0.08
    Activations Density 0.033%

    No Known Activations