© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37054
    Prev
    Next
    INDEX
    Explanations

    det followed by specific endings

    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
    ģ
    -0.12
    æł·çļĦ
    -0.10
    娥
    -0.10
    -0.10
     наг
    -0.09
    oris
    -0.09
     оÑĤз
    -0.09
    erm
    -0.09
    ¦
    -0.09
    趾
    -0.09
    POSITIVE LOGITS
    ected
    0.12
    entions
    0.11
    erring
    0.10
    ters
    0.10
    ched
    0.10
    ectors
    0.10
    ted
    0.10
    annt
    0.10
    å®ļäºĨ
    0.09
    ached
    0.09
    Activations Density 0.048%

    No Known Activations