© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51047
    Prev
    Next
    INDEX
    Explanations

    aid in

    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
    omaly
    -0.10
     Ñĥме
    -0.10
    ymi
    -0.09
    ANNOT
    -0.09
    SCP
    -0.09
    [".
    -0.09
    obia
    -0.08
    ADDING
    -0.08
    ellar
    -0.08
     Mahar
    -0.08
    POSITIVE LOGITS
    umpy
    0.09
    鸳
    0.08
    éĺĹ
    0.08
    鬼
    0.08
    æĤ¦
    0.08
    èħ¥
    0.08
    åIJĥçļĦ
    0.08
    gua
    0.08
    voy
    0.08
    bid
    0.08
    Activations Density 0.026%

    No Known Activations