© 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. 18521
    Prev
    Next
    INDEX
    Explanations

    prediction, classification, model training

    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
    æĹłåĬĽ
    -0.09
     convo
    -0.08
    佯
    -0.08
     cord
    -0.08
    çĮ±
    -0.08
    çī¹åĪ«å£°æĺİ
    -0.08
    积
    -0.08
     hug
    -0.08
    åĮ®ä¹ı
    -0.08
    adr
    -0.08
    POSITIVE LOGITS
    è¾ĵåĩº
    0.09
    شا
    0.09
    ỳ
    0.09
     trained
    0.09
    éħ£
    0.09
    罩
    0.09
    好åĿı
    0.09
     predictions
    0.09
     Hind
    0.09
     hind
    0.09
    Activations Density 0.143%

    No Known Activations