© 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. 16956
    Prev
    Next
    INDEX
    Explanations

    operation or operating method

    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
    æĬ±
    -0.10
    agal
    -0.10
    ลม
    -0.09
    olson
    -0.09
    åijĭ
    -0.09
    æ¿Ĵ
    -0.08
    伺
    -0.08
    æľīæĦı
    -0.08
    çħ³
    -0.08
    expert
    -0.08
    POSITIVE LOGITS
    (Operation
    0.11
     Oper
    0.10
    (operation
    0.10
     Operation
    0.10
    使人
    0.09
     OPER
    0.09
    -operation
    0.09
    .oper
    0.09
     operation
    0.09
    è¿IJèIJ¥
    0.08
    Activations Density 0.109%

    No Known Activations