© 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. 26839
    Prev
    Next
    INDEX
    Explanations

    phrases for describing or citing

    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
    说è¿ĩ
    -0.10
    说äºĨ
    -0.10
    弧
    -0.09
    åĭ¿
    -0.09
    çħ§å°Ħ
    -0.09
     tá»ij
    -0.08
    说çļĦæĺ¯
    -0.08
    çļĦ羣å®ŀ
    -0.08
    æľĢéķ¿
    -0.08
    åıij表äºĨ
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸ī个
    0.09
    pole
    0.09
    èĢĮè¨Ģ
    0.09
    chia
    0.09
     forth
    0.09
    çĨ¬
    0.08
    æĥħåĨµæĿ¥çľĭ
    0.08
    åĢ¾
    0.08
     Slee
    0.08
    æŀĦ
    0.08
    Activations Density 0.014%

    No Known Activations