© 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. 32734
    Prev
    Next
    INDEX
    Explanations

    goes beyond

    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
    ister
    -0.09
    ä¿®åħ»
    -0.09
    åĪ°ä½į
    -0.08
    æľĢåIJĪéĢĤ
    -0.07
     intervening
    -0.07
     trì
    -0.07
     dw
    -0.07
     Baz
    -0.07
    §
    -0.07
    .perform
    -0.07
    POSITIVE LOGITS
     beyond
    0.27
    ä¸įä»ħä»ħæĺ¯
    0.27
    ä¸įä»ħä»ħ
    0.26
    ä¸įåıªæĺ¯
    0.25
     Beyond
    0.23
    Beyond
    0.23
    eyond
    0.20
    以å¤ĸ
    0.20
    ä¸įæŃ¢
    0.20
    è¶ħåĩº
    0.20
    Activations Density 0.086%

    No Known Activations