© 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. 49638
    Prev
    Next
    INDEX
    Explanations

    quantities (more or less)

    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
    汨
    -0.10
    ัส
    -0.10
    ä»Ģä¹Īæł·
    -0.10
    otas
    -0.10
    好è¿IJ
    -0.10
    汩
    -0.10
    çİĩè¾¾
    -0.10
    ãģ¾ãģ¾
    -0.09
    tim
    -0.09
    åıijè´¢
    -0.09
    POSITIVE LOGITS
    çļĦæŶéĹ´éĩĮ
    0.11
    rag
    0.08
     depending
    0.07
    hen
    0.07
    袤
    0.07
    FW
    0.07
     NRA
    0.07
    eter
    0.07
    ansi
    0.07
    IOR
    0.07
    Activations Density 0.029%

    No Known Activations