© 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. 62381
    Prev
    Next
    INDEX
    Explanations

    pleased to announce / with

    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
     же
    -0.09
    elsen
    -0.09
    ged
    -0.09
    thew
    -0.09
    ted
    -0.09
    天涯
    -0.09
    urd
    -0.08
    ied
    -0.08
    geh
    -0.08
    ived
    -0.08
    POSITIVE LOGITS
    fully
    0.13
    antic
    0.10
    wyn
    0.10
    ably
    0.10
     جدا
    0.10
    ä¸įå·²
    0.09
    ocol
    0.09
     rÃłng
    0.09
    IOUS
    0.09
    еÑĪ
    0.09
    Activations Density 0.005%

    No Known Activations