© 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. 18390
    Prev
    Next
    INDEX
    Explanations

    Irish local and national terms

    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
    éĽĦåİļ
    -0.09
    åIJĦæł·
    -0.09
    åħ¥æĪ·
    -0.08
    1
    -0.08
    æĮĤ
    -0.08
    Echo
    -0.08
    æ°´æĻ¶
    -0.08
    7
    -0.08
    0
    -0.08
    åģ¥
    -0.08
    POSITIVE LOGITS
    åĸľ
    0.10
    çĿ¦
    0.10
    åIJĽ
    0.09
     kino
    0.09
     Bundy
    0.09
    çī©åĵģ
    0.09
    CORD
    0.09
    castle
    0.09
    èĪĨæĥħ
    0.09
     Tape
    0.08
    Activations Density 0.169%

    No Known Activations