© 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. 62229
    Prev
    Next
    INDEX
    Explanations

    Ragnarok and related words

    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
    è¾Ļ
    -0.10
    undy
    -0.10
    使人
    -0.09
    immel
    -0.09
    atest
    -0.09
    åĪ®
    -0.09
    ç¢į
    -0.09
    仪表
    -0.09
    inel
    -0.09
    纳
    -0.09
    POSITIVE LOGITS
    å½ĵæĪij们
    0.10
    壤
    0.09
    ings
    0.09
    çŁ¥æĥħ
    0.09
    izu
    0.09
    æĩĤ
    0.08
    èĬĿ
    0.08
    åŃIJéĩĮ
    0.08
    yro
    0.08
    ung
    0.08
    Activations Density 0.003%

    No Known Activations