© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52412
    Prev
    Next
    INDEX
    Explanations

    specifically "of" followed by "the"

    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
    çłº
    -0.11
    IRC
    -0.10
    æīĢå±ŀ
    -0.09
    uco
    -0.09
    è®°ä½ı
    -0.09
     Ñĥзна
    -0.09
    #{@
    -0.09
    antan
    -0.09
    odate
    -0.09
     маÑģÑĤеÑĢ
    -0.08
    POSITIVE LOGITS
    åIJįåı«
    0.18
    åIJį为
    0.15
    åı«åģļ
    0.12
     viz
    0.11
    åij½åIJį为
    0.11
    viz
    0.10
    称为
    0.10
     namely
    0.10
     called
    0.10
    ductor
    0.09
    Activations Density 0.755%

    No Known Activations