© 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. 61089
    Prev
    Next
    INDEX
    Explanations

    following definitions

    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
    çĶļèĩ³æĺ¯
    -0.10
    èĢĮå·²
    -0.10
    éĨº
    -0.09
    æ¯ķç«Ł
    -0.09
    çĶļèĩ³
    -0.09
    elper
    -0.09
    BASH
    -0.08
    磺
    -0.08
    ä¸įèĩ³äºİ
    -0.08
    è¿Ļæł·æīįèĥ½
    -0.08
    POSITIVE LOGITS
    åIJĮæł·æĺ¯
    0.15
    åĪĻæĺ¯
    0.14
     ìĹŃìĭľ
    0.13
    åIJĮæł·
    0.12
    åĪĻ
    0.12
     ebenfalls
    0.12
     similarly
    0.11
     meanwhile
    0.11
    ä¹ŁåIJĮæł·
    0.11
     likewise
    0.11
    Activations Density 0.147%

    No Known Activations