© 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. 27350
    Prev
    Next
    INDEX
    Explanations

    oral or verbal communication

    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
    åıĬåħ¶
    -0.09
     ostr
    -0.09
    é¢ĺæĿIJ
    -0.09
    ãģıãĤĭ
    -0.08
    Pu
    -0.08
     Stück
    -0.08
    UnderTest
    -0.08
     transf
    -0.08
     Merrill
    -0.07
     Anthem
    -0.07
    POSITIVE LOGITS
    ä¼ļè®®ä¸Ĭ
    0.10
    /by
    0.09
    ÑĨе
    0.09
    æĨij
    0.09
    æĻ¯è§Ĥ
    0.09
    é¢Ħ订
    0.09
    è¿Ļç¬Ķ
    0.08
    èħ®
    0.08
    åĩŃ
    0.08
    ITY
    0.08
    Activations Density 0.015%

    No Known Activations