© 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. 48661
    Prev
    Next
    INDEX
    Explanations

    proceedings or proceed action

    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
    ï¸ı
    -0.11
     же
    -0.10
    çĸĹç¨ĭ
    -0.09
    оÑģÑĮ
    -0.09
    éĽĦåİļ
    -0.09
    辫
    -0.09
    ä»ĩæģ¨
    -0.09
    paces
    -0.09
    å§ijå¨ĺ
    -0.09
    ies
    -0.09
    POSITIVE LOGITS
    EDURE
    0.12
    eming
    0.12
    esa
    0.11
    emente
    0.11
    stral
    0.10
    edly
    0.10
    urement
    0.09
    ÙĨج
    0.09
    ester
    0.09
     TForm
    0.09
    Activations Density 0.029%

    No Known Activations