© 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. 56261
    Prev
    Next
    INDEX
    Explanations

    picnic area/tables

    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
    chaft
    -0.09
    åģıåģı
    -0.09
    pes
    -0.08
    iller
    -0.08
    mith
    -0.08
    dddd
    -0.08
    ptr
    -0.08
    æµħ
    -0.08
    aven
    -0.08
    imos
    -0.08
    POSITIVE LOGITS
    etty
    0.11
    æ¡Įä¸Ĭ
    0.09
    çĭİ
    0.09
    æĭ®
    0.09
    ะ
    0.09
    _Framework
    0.09
    æŶåħī
    0.09
    æľīåºıæİ¨è¿Ľ
    0.09
    æĸijæĸĵ
    0.09
    å¼ıçļĦ
    0.09
    Activations Density 0.003%

    No Known Activations