© 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. 49684
    Prev
    Next
    INDEX
    Explanations

    determine if or whether

    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¸ĵ
    -0.10
    åģıåIJij
    -0.10
    razier
    -0.10
    /of
    -0.10
    plier
    -0.10
    æİĺ
    -0.10
    .Manager
    -0.10
    æģķ
    -0.10
    /to
    -0.09
    æ¢
    -0.09
    POSITIVE LOGITS
     whether
    0.12
    æĺ¯åIJ¦
    0.12
    æĺ¯åIJ¦æľī
    0.10
     Jag
    0.09
    羣åģĩ
    0.09
     Whether
    0.09
     æĺ¯åIJ¦
    0.08
    Whether
    0.08
    çĶĦ
    0.08
    ä¸Ģè§Ĵ
    0.08
    Activations Density 0.057%

    No Known Activations