© 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. 63230
    Prev
    Next
    INDEX
    Explanations

    words starting with ed

    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
    sWith
    -0.09
     Herald
    -0.09
    åģļ强
    -0.09
    itis
    -0.09
    hood
    -0.09
    AffineTransform
    -0.09
     ÑĥпÑĢав
    -0.09
    nger
    -0.08
    scale
    -0.08
     Dise
    -0.08
    POSITIVE LOGITS
    ÑĥÑī
    0.10
    mond
    0.10
    èī¯å¥½
    0.09
    ialog
    0.09
    minster
    0.08
    irect
    0.08
    enti
    0.08
    ystone
    0.08
     Willie
    0.08
    emption
    0.08
    Activations Density 0.016%

    No Known Activations