© 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. 62658
    Prev
    Next
    INDEX
    Explanations

    verbs denoting ongoing actions/states

    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
    ä½ľä¸ºä¸ĢåIJį
    -0.09
    lage
    -0.09
    ä¸İåħ¶ä»ĸ
    -0.09
    rite
    -0.09
    大家ä¸Ģèµ·
    -0.09
    زاÙĦ
    -0.08
    æIJŃ
    -0.08
    åĪ®
    -0.08
    鸥
    -0.08
    ä½ľä¸ºä¸Ģ个
    -0.08
    POSITIVE LOGITS
     themselves
    0.13
     whom
    0.09
    æī¹è¯Ħ
    0.09
     who
    0.09
     BOTH
    0.09
    类似
    0.09
    either
    0.09
     both
    0.08
    anas
    0.08
    纷纷
    0.08
    Activations Density 0.126%

    No Known Activations