© 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. 49548
    Prev
    Next
    INDEX
    Explanations

    story

    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
    à¹ģà¸Ĺ
    -0.09
    NEY
    -0.09
     Redistribution
    -0.09
    RowCount
    -0.09
    ities
    -0.09
    ords
    -0.08
    statements
    -0.08
    åIJĦèĩªçļĦ
    -0.08
    heimer
    -0.08
    Surv
    -0.08
    POSITIVE LOGITS
    agger
    0.12
    ราว
    0.11
    allis
    0.10
    ateg
    0.09
     зай
    0.09
    anghai
    0.09
    iling
    0.09
    è¿Ļæł·çļĦè¯Ŀ
    0.09
    ä¼¢
    0.09
    atical
    0.08
    Activations Density 0.023%

    No Known Activations