© 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. 35904
    Prev
    Next
    INDEX
    Explanations

    nutrients, vitamins, metals

    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
    Ñģов
    -0.09
    _indent
    -0.09
    دÙī
    -0.08
    ä¹ĭè·¯
    -0.08
    hea
    -0.08
    rapper
    -0.08
    çĹ´
    -0.08
    vent
    -0.08
    amat
    -0.08
    è°ļ
    -0.08
    POSITIVE LOGITS
     nutrients
    0.12
    èIJ¥åħ»
    0.12
    诸å¦Ĥ
    0.10
    å¾®éĩıåħĥç´ł
    0.10
    æĿĤè´¨
    0.10
    è¦ģç´ł
    0.10
    æĪIJ份
    0.10
    åĮħæĭ¬
    0.10
    æłĭ
    0.09
     vitamins
    0.09
    Activations Density 0.291%

    No Known Activations