© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7592
    Prev
    Next
    INDEX
    Explanations

    rewarding, fulfilling experiences

    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
    èĪ«
    -0.10
    ../../../
    -0.09
    çĮĽçĥĪ
    -0.09
     мил
    -0.09
    opus
    -0.08
    ically
    -0.08
    æ´Ĺ涤
    -0.08
    à¸Ľà¸²
    -0.08
    大éĻĨ
    -0.08
    è¿Ļæł·è¯´
    -0.08
    POSITIVE LOGITS
    nal
    0.11
    رش
    0.10
    ardin
    0.10
    ãģª
    0.09
     оÑĤказ
    0.09
    åįģ足
    0.09
    满满
    0.09
    ingly
    0.09
    æīĢåľ¨
    0.08
    æķ´ä¸ªäºº
    0.08
    Activations Density 0.009%

    No Known Activations