© 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. 55475
    Prev
    Next
    INDEX
    Explanations

    trace

    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
    ted
    -0.10
    è¦ģçŁ¥éģĵ
    -0.09
     rendre
    -0.09
    æ®ĸ
    -0.09
    spa
    -0.09
    éħª
    -0.09
    sher
    -0.09
    frey
    -0.09
     fatt
    -0.09
    ÑĪек
    -0.08
    POSITIVE LOGITS
    able
    0.12
    ability
    0.12
    backs
    0.12
    迹
    0.11
    æ¶İ
    0.11
    ãĥĥãĥĹ
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    less
    0.10
    heet
    0.10
    heets
    0.10
    Activations Density 0.023%

    No Known Activations