© 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. 33684
    Prev
    Next
    INDEX
    Explanations

    series

    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
    ters
    -0.11
    ted
    -0.11
    sworth
    -0.10
    soever
    -0.10
    OrCreate
    -0.09
    ardo
    -0.09
    swing
    -0.09
    ÑĤан
    -0.09
    tal
    -0.09
    owski
    -0.08
    POSITIVE LOGITS
    ä¸Ľä¹¦
    0.11
    EGIN
    0.10
    heck
    0.10
    zech
    0.10
    好è¿IJ
    0.09
    ple
    0.09
    nyder
    0.09
    hood
    0.09
    esan
    0.09
    plen
    0.09
    Activations Density 0.061%

    No Known Activations