© 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. 55691
    Prev
    Next
    INDEX
    Explanations

    field of invention

    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
    泡
    -0.09
    åħ«åŃĹ
    -0.08
    æĭĩ
    -0.08
     duro
    -0.08
    åĽ½åľŁèµĦæºIJ
    -0.08
    ä¸įä¸Ĭ
    -0.07
    çĸĨ
    -0.07
    æĭ¥æĬ±
    -0.07
    dob
    -0.07
    oe
    -0.07
    POSITIVE LOGITS
    åģ»
    0.10
    /animate
    0.10
     Äijèn
    0.10
    .require
    0.10
    æľīæľŁ
    0.10
    èĽŁ
    0.10
    éĢ¶
    0.09
    iec
    0.09
    isol
    0.09
    .Multiline
    0.09
    Activations Density 0.012%

    No Known Activations