© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8744
    Prev
    Next
    INDEX
    Explanations

    what better way to

    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
    éĥ½æľī
    -0.09
    åĹ¯
    -0.09
    èĭ±çī¹
    -0.09
    rium
    -0.09
    ye
    -0.08
    MEA
    -0.08
    亲çĪ±çļĦ
    -0.08
    orld
    -0.08
    ary
    -0.08
    æĽ´ä¸º
    -0.08
    POSITIVE LOGITS
     nơi
    0.10
    .EVENT
    0.10
    人éĢī
    0.09
    _PD
    0.09
    ä»İ严治
    0.08
    chl
    0.08
    海滨
    0.08
     ìĸĺ
    0.08
    æ¤ħ
    0.08
    /latest
    0.08
    Activations Density 0.015%

    No Known Activations