© 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. 23020
    Prev
    Next
    INDEX
    Explanations

    rare, rarity, uncommon

    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
    allee
    -0.10
     обÑıзаÑĤелÑĮ
    -0.09
    moz
    -0.09
    好åĥı
    -0.09
     cps
    -0.08
    æĦı大
    -0.08
     Recomm
    -0.08
    شر
    -0.08
    aze
    -0.08
    дÑĢ
    -0.08
    POSITIVE LOGITS
    ç½ķè§ģ
    0.24
    å°ijè§ģ
    0.22
     rare
    0.21
    ç¨Ģ缺
    0.21
     rarity
    0.20
    Rare
    0.19
    ç¨Ģ
    0.19
     Rare
    0.19
    éļ¾å¾Ĺ
    0.18
     hiếm
    0.16
    Activations Density 0.176%

    No Known Activations