© 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. 2050
    Prev
    Next
    INDEX
    Explanations

    yolk and white ingredients

    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
    erset
    -0.10
    _M
    -0.09
    é£İ鼨
    -0.09
    æĬĬèĩªå·±çļĦ
    -0.09
    éĥĬ
    -0.09
    é£İåIJ¹
    -0.08
    åĬ£
    -0.08
    -Apr
    -0.08
    .t
    -0.08
    鹿
    -0.08
    POSITIVE LOGITS
    åĦ¿
    0.12
    tern
    0.11
    lessly
    0.10
    ted
    0.10
    erne
    0.10
    åħĴ
    0.09
    lege
    0.09
    è¾ĸ
    0.09
    宿
    0.09
    less
    0.09
    Activations Density 0.007%

    No Known Activations