© 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. 31540
    Prev
    Next
    INDEX
    Explanations

    daisy, chrysanthemum, aster

    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
    æĭ¢
    -0.10
    çłĶåıijæĬķåħ¥
    -0.09
    ä¸ĢæĶ¯
    -0.09
    第ä¸Ģéĥ¨
    -0.09
    æľŁæľ«
    -0.09
    å¡ĺ
    -0.08
    uger
    -0.08
    黾
    -0.08
    åħĢ
    -0.08
    ÙĪØ®
    -0.08
    POSITIVE LOGITS
    åįī
    0.10
    åħ¨å¤©
    0.09
    éĻIJè´Ń
    0.09
     DPR
    0.09
    å´ĩ
    0.09
    Plug
    0.09
     Plug
    0.09
     reim
    0.09
    丼
    0.09
    ÙħÙĬØ©
    0.09
    Activations Density 0.044%

    No Known Activations