© 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. 11835
    Prev
    Next
    INDEX
    Explanations

    sur- prefix combinations

    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
    æĭĬ
    -0.09
    orus
    -0.09
    обÑĭ
    -0.09
    æľīæĽ´å¥½çļĦ
    -0.08
    sterdam
    -0.08
    ÑĢом
    -0.08
     michael
    -0.08
    rys
    -0.08
    chal
    -0.08
    ãĥķãĥ«
    -0.08
    POSITIVE LOGITS
     kiá»ĩn
    0.10
    ulence
    0.10
    veys
    0.10
    å°±è¿ŀ
    0.10
    ties
    0.10
    jective
    0.10
    uously
    0.10
    veillance
    0.10
    วà¸Ķ
    0.10
    rogate
    0.10
    Activations Density 0.026%

    No Known Activations