© 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. 55395
    Prev
    Next
    INDEX
    Explanations

    names ending in ton, Mills, ins, son, jan, ver, ger

    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
    pdb
    -0.10
     полов
    -0.09
    ces
    -0.09
    resh
    -0.08
    ily
    -0.08
    åĹ½
    -0.08
    ITO
    -0.08
    aina
    -0.08
    YST
    -0.08
    agenda
    -0.08
    POSITIVE LOGITS
    æľīè¿ĩ
    0.09
     reservoir
    0.09
    лей
    0.08
    aldo
    0.08
    ниÑĨÑĭ
    0.08
    ложений
    0.08
    æĶ»åĬ¿
    0.08
     Loft
    0.08
    ä»ĩæģ¨
    0.08
    åºľ
    0.08
    Activations Density 0.007%

    No Known Activations