© 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. 32713
    Prev
    Next
    INDEX
    Explanations

    vegetables, food ingredients, cuts

    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
    utive
    -0.09
    èħ¾
    -0.09
    é¾Ļ头
    -0.08
    uate
    -0.08
    uated
    -0.08
    isempty
    -0.08
    èĮ§
    -0.08
    æĽ²æĬĺ
    -0.08
     dct
    -0.08
    毡
    -0.08
    POSITIVE LOGITS
    åĪĩæĪIJ
    0.13
    åĪĩ
    0.12
    çĤ¸
    0.11
    обÑĢаÐ
    0.10
    åīĶ
    0.09
    åŀł
    0.09
    éĬ®
    0.09
    åĩ°
    0.08
    éºŁ
    0.08
    arts
    0.08
    Activations Density 0.042%

    No Known Activations