© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19464
    Prev
    Next
    INDEX
    Explanations

    la followed by another word

    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
    esti
    -0.10
    ол
    -0.10
    rist
    -0.09
    laus
    -0.09
    rary
    -0.09
    imet
    -0.09
    nel
    -0.09
     Aires
    -0.08
    vara
    -0.08
    alem
    -0.08
    POSITIVE LOGITS
    uded
    0.11
    unched
    0.10
    oretical
    0.09
    cona
    0.09
    UNCH
    0.09
    urent
    0.09
    ;;;;
    0.09
    /interface
    0.09
    ughter
    0.08
    æľ½
    0.08
    Activations Density 0.020%

    No Known Activations