© 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. 37624
    Prev
    Next
    INDEX
    Explanations

    meal processing or dietary components

    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
    es
    -0.11
    .Kind
    -0.08
    anon
    -0.08
    اخ
    -0.08
    们
    -0.08
    缺çĤ¹
    -0.08
    鹬
    -0.07
    éĴ¥
    -0.07
    é£İåı£
    -0.07
     blend
    -0.07
    POSITIVE LOGITS
    ToWorld
    0.11
    irror
    0.11
    ayne
    0.10
    æĤ±
    0.10
    chal
    0.09
    ç¾Ķ
    0.09
     Vive
    0.09
    羯
    0.09
    swer
    0.09
    ivre
    0.09
    Activations Density 0.006%

    No Known Activations