© 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. 17603
    Prev
    Next
    INDEX
    Explanations

    agricultural implements

    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
    港澳
    -0.09
    å¾ģ
    -0.08
    ward
    -0.08
     оÑĦоÑĢмлен
    -0.08
    å¢ŀè¿Ľ
    -0.08
    åIJį人
    -0.08
    çĶ¨äºİ
    -0.08
    åĬ²
    -0.08
    æĪIJ人
    -0.08
    andes
    -0.08
    POSITIVE LOGITS
    èĩªè´Ł
    0.09
    大è±Ĩ
    0.09
    麻
    0.09
    æŃī
    0.09
     nghiá»ĩp
    0.08
    edition
    0.08
    æĴŃç§į
    0.08
     margins
    0.08
    å·¥ç¨ĭå¸Ī
    0.08
     Technologies
    0.08
    Activations Density 0.167%

    No Known Activations