© 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. 1367
    Prev
    Next
    INDEX
    Explanations

    crucial component or stage

    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
    sWith
    -0.09
    åŁºæľ¬æĥħåĨµ
    -0.09
    ToInt
    -0.09
     LGPL
    -0.09
    apia
    -0.09
    竺
    -0.09
    eing
    -0.09
    äºĨ个
    -0.09
    kir
    -0.08
    olu
    -0.08
    POSITIVE LOGITS
    ly
    0.15
     обÑĢазом
    0.12
    æĹłæ¯Ķ
    0.11
    æĢ§çļĦ
    0.11
    mente
    0.11
    ä¸ĩåĪĨ
    0.10
    è¿Ļä¸ĢçĤ¹
    0.10
    ties
    0.10
    ité
    0.10
    ä¸Ģé»ŀ
    0.10
    Activations Density 0.014%

    No Known Activations