© 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. 7140
    Prev
    Next
    INDEX
    Explanations

    Walmart, Mart

    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
    edList
    -0.11
    wald
    -0.11
    ettle
    -0.10
    lessly
    -0.09
    obic
    -0.09
    ached
    -0.09
    åIJĮåŁİ
    -0.09
    è¨Ĺ
    -0.09
    rylic
    -0.09
    è¶Ĭå¤ļ
    -0.09
    POSITIVE LOGITS
    ä¸Ģ件
    0.09
    ä¼ģ
    0.08
    iska
    0.08
    ç¬Ļ
    0.08
    å¼Ħ
    0.08
    ifications
    0.08
    è°¯
    0.08
    ires
    0.08
    ç¹ģå¿Ļ
    0.08
    ision
    0.08
    Activations Density 0.003%

    No Known Activations