© 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. 7194
    Prev
    Next
    INDEX
    Explanations

    financial instruments, contracts, shipments, blades

    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
    缴è¾ĸ
    -0.10
    ashing
    -0.09
    年纪
    -0.09
    ç¾²
    -0.09
    è§ľ
    -0.09
    èµĦ
    -0.09
     loft
    -0.08
    æľīå¾Ī大
    -0.08
    çīĩåĮº
    -0.08
    åŁĴ
    -0.08
    POSITIVE LOGITS
    esy
    0.10
    æľĪæľ«
    0.09
    æıIJåīį
    0.09
    oca
    0.09
    ailer
    0.08
    åĪĹ
    0.08
    ãĤ
    0.08
    æĬ¥åijĬæľŁåĨħ
    0.08
    anton
    0.08
    å®ŀä½ĵ
    0.08
    Activations Density 0.034%

    No Known Activations