© 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. 32151
    Prev
    Next
    INDEX
    Explanations

    raft, barge, craft

    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
    è§ī
    -0.10
    rist
    -0.09
    atti
    -0.09
    ãĥķãĥªãĥ¼
    -0.09
    ä¸Ģé¢Ĺ
    -0.09
    ariat
    -0.08
    yor
    -0.08
    aries
    -0.08
    hop
    -0.08
    é¢Ĺ
    -0.08
    POSITIVE LOGITS
    stry
    0.10
    çŃı
    0.10
    (Photo
    0.09
    ç«ŀæĬĢ
    0.09
    èĩ¾
    0.09
    à¸Ķำ
    0.09
    ÑĥÑĩ
    0.08
    à¸Ńà¸Ļ
    0.08
    инг
    0.08
    oning
    0.08
    Activations Density 0.004%

    No Known Activations