© 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. 48517
    Prev
    Next
    INDEX
    Explanations

    pot, oven, pan, teapot

    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
    uant
    -0.09
    çŃĭ
    -0.09
    (MPI
    -0.09
    ure
    -0.08
    erman
    -0.08
     Españ
    -0.08
    erte
    -0.08
    家ä¼Ļ
    -0.08
    otime
    -0.08
    ymm
    -0.08
    POSITIVE LOGITS
    assium
    0.11
    èĻ±
    0.09
    ieres
    0.09
    balls
    0.09
    æĺı
    0.09
    mith
    0.09
    çĦĸ
    0.09
    çĤĸ
    0.09
    æĸ°å½¢åĬ¿ä¸ĭ
    0.09
    ãģĿãĤĮãģ«
    0.09
    Activations Density 0.006%

    No Known Activations