© 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. 39101
    Prev
    Next
    INDEX
    Explanations

    acuity, volume, intensity, performance, richness

    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
    ness
    -0.09
    interop
    -0.09
    à¹ģà¸Ĺ
    -0.08
    æĦıåij³
    -0.08
    ordo
    -0.08
    ä¹ĭå¿ĥ
    -0.08
    -thumbnails
    -0.08
    æĢ§çļĦ
    -0.08
    ä½ľåĵģåĨħ容
    -0.08
    avery
    -0.08
    POSITIVE LOGITS
    SEC
    0.09
     parity
    0.09
    egan
    0.09
    æѤæĸĩ
    0.09
    trap
    0.08
    æĪijä¸įçŁ¥éģĵ
    0.08
    .tie
    0.08
    çİĭèĢħ
    0.08
    гон
    0.08
    DEC
    0.08
    Activations Density 0.378%

    No Known Activations