© 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. 17720
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating location or relation

    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
    æĸ°å½¢åĬ¿
    -0.09
    kan
    -0.08
     ghé
    -0.08
    YTE
    -0.08
    åĹľ
    -0.08
     оÑĤд
    -0.08
    icamente
    -0.08
    ift
    -0.08
    çŁ¥æĥħ
    -0.08
    ifen
    -0.08
    POSITIVE LOGITS
    社ä¼ļå®ŀè·µ
    0.09
    éªĦ
    0.09
    æīİ
    0.08
    ÑģÑĤавка
    0.08
    大家éĥ½åľ¨
    0.08
    çĦ¦
    0.08
    ellas
    0.08
    ãĤ¹ãĤ¿
    0.08
    æ¯ķç«Ł
    0.08
    ä¹Ĵä¹ĵ
    0.08
    Activations Density 0.274%

    No Known Activations