© 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. 26608
    Prev
    Next
    INDEX
    Explanations

    nwjs or node-webkit window

    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
    åĥ§
    -0.09
    æĻºèĥ½
    -0.09
     smart
    -0.09
    Smart
    -0.08
     Smart
    -0.08
    ç±Ģ
    -0.08
    åģļè¿ĩ
    -0.08
    碰
    -0.08
    æĴŃæĬ¥
    -0.08
    quee
    -0.08
    POSITIVE LOGITS
     Packing
    0.11
     packing
    0.10
    æ¡ĮéĿ¢
    0.10
    à¹ģà¸ľ
    0.10
    åĮħè£ħ
    0.10
    .icons
    0.10
    .Ribbon
    0.09
    æĻ¨
    0.09
    æ¹ĸåĮº
    0.09
    elter
    0.09
    Activations Density 0.380%

    No Known Activations