© 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. 18442
    Prev
    Next
    INDEX
    Explanations

    Slashdot videos

    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
    åįļä¼ļ
    -0.09
    aque
    -0.09
    Occup
    -0.08
     Alphabet
    -0.08
    alphabet
    -0.08
    alien
    -0.08
     alphabet
    -0.08
    ç³ł
    -0.08
    ected
    -0.08
    eren
    -0.08
    POSITIVE LOGITS
     vụ
    0.10
    åĤį
    0.09
     cứu
    0.09
    轧
    0.08
    etails
    0.08
    pliant
    0.08
    æĪIJ为ä¸ĢåIJį
    0.08
    거리
    0.08
    è²Ĭ
    0.08
     polo
    0.08
    Activations Density 0.001%

    No Known Activations