© 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. 61967
    Prev
    Next
    INDEX
    Explanations

    eBay and PayPal transactions

    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
    ality
    -0.12
    ={({
    -0.10
    ä»ĸèĩªå·±
    -0.10
    æľīéĴ±
    -0.09
     WARRANTY
    -0.08
    umbing
    -0.08
    ITED
    -0.08
    æ¦ľ
    -0.08
    sr
    -0.08
    uring
    -0.08
    POSITIVE LOGITS
    asics
    0.11
    ç§ijæķĻ
    0.10
    rides
    0.09
    isches
    0.09
    æ±Ĭ
    0.09
    ramid
    0.09
    å¾Ĺèµ·
    0.08
    xEE
    0.08
    袱
    0.08
    pping
    0.08
    Activations Density 0.003%

    No Known Activations