© 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. 49418
    Prev
    Next
    INDEX
    Explanations

    guard or guards and related words

    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
    TING
    -0.10
    pra
    -0.10
    elly
    -0.09
    ting
    -0.09
    sembling
    -0.09
    æijĨåľ¨
    -0.09
    bbie
    -0.09
    lish
    -0.09
    egan
    -0.09
    icker
    -0.09
    POSITIVE LOGITS
    iola
    0.13
    edList
    0.11
    edly
    0.11
    rail
    0.10
    less
    0.10
    rails
    0.10
     against
    0.09
    isplay
    0.09
    ome
    0.09
    iveness
    0.09
    Activations Density 0.019%

    No Known Activations